Translation device and translation method

Abstract

A translation device (1) is configured so as to comprise: an original text acquisition unit (11) that acquires an original text to be translated; a first translation unit (12) that causes the original text acquired by the original text acquisition unit (11) to be translated into a first language; a back translation unit (13) that causes the translated text by the first translation unit (12) to be translated back; a display processing unit (16) that causes a display device (3) to display the translated-back text by the back translation unit (13); and a correction reception unit (14) that receives correction of the original text after the translated-back text is displayed by the display processing unit (16). The translation device (1) also comprises a second translation unit (15) that, when the correction reception unit (14) receives the correction of the original text, causes the corrected original text received by the correction reception unit (14) to be translated into a second language.

Description

Technical Field

[0001] The present disclosure relates to a translation apparatus and a translation method.

Background Art

[0002] There are translation apparatuses that translate an original text to be translated. As such a translation apparatus, for example, Patent Document 1 discloses a translation apparatus including a processing control unit that translates an original text in a source language into a first language, displays a translated text in the first language on a screen, back-translates the translated text in the first language into the source language, and displays the back-translated text in the source language on a screen.

Prior Art Literature

Patent Literature

[0003]

Patent Document 1

Summary of Invention

Problem to be Solved by Invention

[0004] The translation apparatus disclosed in Patent Document 1 only contemplates translating an original text in a source language into a single first language. Therefore, in order to translate an original text in a source language into a plurality of languages, it is necessary to use a plurality of the translation apparatuses disclosed in Patent Document 1. When a plurality of the translation apparatuses disclosed in Patent Document 1 are used to translate an original text in a source language into a plurality of languages, if the back-translated text does not match the user's intention, the user needs to correct the original text for each of the plurality of target languages. As a result, the user has to perform similar correction work many times, and it takes time to complete the translation into a plurality of languages.

[0005] This disclosure was made to solve the above-mentioned problems, and aims to provide a translation device that can translate source text into multiple languages ​​and reduce the time required for translation into multiple languages. [Means for solving the problem]

[0006] The translation device relating to this disclosure includes a source text acquisition unit that acquires the source text to be translated, and a unit that translates the source text acquired by the source text acquisition unit into a first language. do The first translation section and the translation by the first translation section are translated back. do The translation device comprises a wrap-around translation unit, a display processing unit that displays the wrap-around translated text from the wrap-around translation unit on a display device, and a correction acceptance unit that accepts corrections to the original text after the wrap-around translated text has been displayed by the display processing unit. Furthermore, when the correction acceptance unit accepts a correction to the original text, the translation device translates the corrected original text received by the correction acceptance unit into a second language. do It includes a second translation section. When the first translation unit translates the source text obtained by the source text acquisition unit into the first language, it refers to a specialized terminology dictionary that records the correspondence between specialized terms and translation information. If a term contained in the source text is a specialized term recorded in the specialized terminology dictionary, and if it obtains information indicating the pronunciation of the specialized term as translation information corresponding to the term contained in the source text from the specialized terminology dictionary, it translates the term contained in the source text to the pronunciation indicated by the obtained information as the translation result into the first language. If it obtains information indicating the translation of the specialized term into the first language as translation information, it translates the term contained in the source text to the translation of the specialized term into the first language. The second translation unit, using information indicating the pronunciation of technical terms as translation information obtained by the first translation unit from a technical term dictionary, translates the technical terms into the second language by converting the pronunciation of the technical terms into phonetic characters corresponding to the second language, if the terms contained in the source text obtained by the source text acquisition unit have been translated into the first language, or by using the information indicating the pronunciation of the technical terms as is. [Effects of the Invention]

[0007] According to this disclosure, the source text to be translated can be translated into multiple languages, and the time required for translation into multiple languages ​​can be reduced. [Brief explanation of the drawing]

[0008] [Figure 1] This is a configuration diagram showing a translation system including a translation device 1 according to Embodiment 1. [Figure 2] This is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 1. [Figure 3] This is a hardware configuration diagram of a computer when the translation device 1 is implemented by software or firmware, etc. [Figure 4] This is a flowchart showing the translation method, which is the processing procedure of the translation device 1. [Figure 5] This is a configuration diagram showing a translation system including a translation device 1 according to Embodiment 2. [Figure 6] It is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 2. [Figure 7] It is a configuration diagram showing a translation system including the translation device 1 according to Embodiment 3. [Figure 8] It is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 3. [Figure 9] It is an explanatory diagram showing an example of technical terms recorded in a technical term dictionary, definitions of the technical terms, readings of the technical terms, and first-language translations of the technical terms. [Figure 10] It is a configuration diagram showing a translation system including the translation device 1 according to Embodiment 4. [Figure 11] It is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 4. [Figure 12] It is an explanatory diagram showing an example of an image capturing a target person to be provided. [Figure 13] It is a configuration diagram showing a translation system including the translation device 1 according to Embodiment 5. [Figure 14] It is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 5. [Figure 15] It is a flowchart showing a translation method which is a processing procedure of the translation device 1. Mode for Carrying Out the Invention

[0009] Hereinafter, in order to describe the present disclosure in more detail, modes for carrying out the present disclosure will be described with reference to the accompanying drawings.

[0010] Embodiment 1. FIG. 1 is a configuration diagram showing a translation system including the translation device 1 according to Embodiment 1. FIG. 2 is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 1. The translation system shown in FIG. 1 includes the translation device 1, a translation engine 2, and a display device 3. The translation apparatus 1 provides an original text to be translated to the translation engine 2, acquires respective translated texts in a plurality of languages from the translation engine 2, and causes the display device 3 to display each of the translated texts. When the original text to be translated is provided from the translation apparatus 1 to the translation engine 2, the translation engine 2 translates the original text into each language and outputs the translated text in each language to the translation apparatus 1. The display device 3 displays the translated texts and the like in the respective languages.

[0011] The translation apparatus 1 includes an original text acquisition unit 11, a first translation unit 12, a round-trip translation unit 13, a correction reception unit 14, a second translation unit 15, and a display processing unit 16. The original text acquisition unit 11 is realized by, for example, an original text acquisition circuit 21 shown in FIG. 2. The original text acquisition unit 11 acquires the original text to be translated. The original text acquisition unit 11 outputs the original text to be translated to each of the first translation unit 12, the correction reception unit 14, the second translation unit 15, and the display processing unit 16.

[0012] The first translation unit 12 is realized by, for example, a first translation circuit 22 shown in FIG. 2. The first translation unit 12 acquires the original text to be translated from the original text acquisition unit 11. The first translation unit 12 causes the original text acquired by the original text acquisition unit 11 to be translated into a first language. Specifically, the first translation unit 12 provides the original text to be translated to the translation engine 2, and acquires the translated text in the first language from the translation engine 2. In the translation system shown in FIG. 1, the translation engine 2 is provided outside the translation apparatus 1. However, this is merely an example, and the translation engine 2 may be provided inside the translation apparatus 1. For example, if the first translation unit 12 includes a translation engine, the first translation unit 12 translates the original text to be translated into the first language. The first translation unit 12 outputs the translated text in the first language to each of the round-trip translation unit 13 and the display processing unit 16.

[0013] The reverse translation unit 13 is implemented, for example, by the reverse translation circuit 23 shown in Figure 2. The return translation unit 13 obtains the translated text in the first language from the first translation unit 12. The reverse translation unit 13 reverses the translation of the first translation unit 12. Reverse translation translates the translation of the first translation unit 12 into the language used in the original text being translated. Specifically, the wrap-around translation unit 13 provides the translation of the first language to the translation engine 2 and obtains the wrap-around translation from the translation engine 2. In the translation system shown in Figure 1, the translation engine 2 is located outside the translation device 1. However, this is just one example, and the translation engine 2 may be located inside the translation device 1. For example, if the reverse translation unit 13 is equipped with a translation engine, the reverse translation unit 13 reverses the translation of the first language text. The wrap-around translation unit 13 outputs the wrap-around translated text to the display processing unit 16.

[0014] The correction acceptance unit 14 is implemented, for example, by the correction acceptance circuit 24 shown in Figure 2. The revision request unit 14 retrieves the source text to be translated from the source text acquisition unit 11. The correction acceptance unit 14 accepts corrections to the original text after the line-wrapped translation is displayed by the display processing unit 16. The revision reception unit 14 outputs the received revised source text to the first translation unit 12 and the second translation unit 15, respectively.

[0015] The second translation unit 15 is implemented, for example, by the second translation circuit 25 shown in Figure 2. The second translation unit 15 retrieves the revised source text from the revision acceptance unit 14 if the revisions have been accepted by the revision acceptance unit 14. The second translation unit 15 retrieves the original Japanese text from the original text retrieval unit 11 if no revisions have been accepted by the revision acceptance unit 14. The second translation unit 15, if the revisions have been accepted by the revision acceptance unit 14, will translate the revised source text accepted by the revision acceptance unit 14 into the second language; if the revisions have not been accepted by the revision acceptance unit 14, it will translate the source text acquired by the source text acquisition unit 11 into the second language. Specifically, the second translation unit 15 provides the translation engine 2 with either the revised source text received by the revision acceptance unit 14 or the source text acquired by the source text acquisition unit 11, and obtains a translated text in the second language from the translation engine 2. In the translation system shown in Figure 1, the translation engine 2 is located outside the translation device 1. However, this is just one example, and the translation engine 2 may also be located inside the translation device 1. For example, if the second translation unit 15 is equipped with a translation engine, the second translation unit 15 translates either the original text after correction by the correction receiving unit 14 or the original text acquired by the original text acquisition unit 11 into the second language. The second translation unit 15 outputs the translated text in the second language to the display processing unit 16.

[0016] The display processing unit 16 is implemented, for example, by the display processing circuit 26 shown in Figure 2. The display processing unit 16 displays the source text to be translated, output from the source text acquisition unit 11, on the display device 3, and displays the translated text in the first language, output from the first translation unit 12, on the display device 3. Furthermore, the display processing unit 16 displays the reversed translation output from the reversed translation unit 13 on the display device 3, and displays the translation in the second language output from the second translation unit 15 on the display device 3.

[0017] In Figure 1, the components of the translation device 1—the source text acquisition unit 11, the first translation unit 12, the reverse translation unit 13, the correction acceptance unit 14, the second translation unit 15, and the display processing unit 16—are assumed to be implemented by dedicated hardware as shown in Figure 2. Specifically, the translation device 1 is assumed to be implemented by a source text acquisition circuit 21, a first translation circuit 22, a reverse translation circuit 23, a correction acceptance circuit 24, a second translation circuit 25, and a display processing circuit 26. Each of the source text acquisition circuit 21, the first translation circuit 22, the reverse translation circuit 23, the correction acceptance circuit 24, the second translation circuit 25, and the display processing circuit 26 can be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof.

[0018] The components of the translation device 1 are not limited to those implemented by dedicated hardware; the translation device 1 may also be implemented by software, firmware, or a combination of software and firmware. Software or firmware is stored as a program in the computer's memory. A computer refers to the hardware that executes programs, and includes, for example, a CPU (Central Processing Unit), GPU (Graphics Processing Unit), central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, processor, or DSP (Digital Signal Processor).

[0019] Figure 3 is a hardware configuration diagram of a computer when the translation device 1 is implemented by software or firmware, etc. If the translation device 1 is implemented by software or firmware, a program is stored in memory 31 that causes the computer to execute the respective processing procedures in the source text acquisition unit 11, the first translation unit 12, the reverse translation unit 13, the correction acceptance unit 14, the second translation unit 15, and the display processing unit 16. The computer's processor 32 then executes the program stored in memory 31.

[0020] Furthermore, Figure 2 shows an example in which each component of the translation device 1 is implemented by dedicated hardware, and Figure 3 shows an example in which the translation device 1 is implemented by software or firmware, etc. However, this is only one example, and some components of the translation device 1 may be implemented by dedicated hardware, while the remaining components may be implemented by software or firmware, etc.

[0021] Next, we will explain the operation of the translation system shown in Figure 1. Figure 4 is a flowchart showing the translation method, which is the processing procedure of the translation device 1. In the translation system shown in Figure 1, for the sake of explanation, we will assume that the source text to be translated is in Japanese, the first language is English, and the second language is Portuguese.

[0022] The source text acquisition unit 11 acquires the Japanese source text as the source text to be translated (step ST1 in Figure 4). For the sake of explanation, we will assume that the original Japanese text obtained was, "Please rotate and check again after reattaching the zipper." The source text acquisition unit 11 outputs the source text to be translated to the first translation unit 12, the correction acceptance unit 14, the second translation unit 15, and the display processing unit 16, respectively. The display processing unit 16 displays the source text to be translated, output from the source text acquisition unit 11, on the display device 3.

[0023] The first translation unit 12 retrieves the Japanese original text from the original text retrieval unit 11. The first translation unit 12 translates the source text obtained by the source text acquisition unit 11 into English, the first language (step ST2 in Figure 4). Specifically, the first translation unit 12 provides the Japanese source text to the translation engine 2 and obtains the English translation from the translation engine 2. The first translation unit 12 outputs the English translation to the line-wrap translation unit 13 and the display processing unit 16, respectively. The display processing unit 16 displays the English translation output from the first translation unit 12 on the display device 3.

[0024] The return translation unit 13 retrieves the English translation from the first translation unit 12. The reverse translation unit 13 reverses the translation of the text by the first translation unit 12 (step ST3 in Figure 4). Specifically, the wrap-around translation unit 13 provides the English translation to the translation engine 2 and retrieves the wrap-around translation from the translation engine 2. The wrap-around translation unit 13 outputs the wrap-around translated text to the display processing unit 16. If the English translation of the above original text is given to translation engine 2, translation engine 2 may output a line-wrapped translation such as, for example, "Reattach the fastener and twist to check." This reversed translation gives the impression that the fastener is being attached twice, which differs from the nuance of the original text. Therefore, the original text needs to be revised and translated again. The display processing unit 16 displays the re-translated text output from the correction reception unit 14 on the display device 3 (step ST4 in Figure 4).

[0025] The correction reception unit 14 retrieves the original Japanese text from the original text retrieval unit 11. The correction request unit 14 is implemented, for example, by a human-machine interface. A user who has reviewed the wrapped translation can correct the original Japanese text by operating the correction request unit 14 if they recognize any nuances between the original text and the wrapped translation.

[0026] When a user modifies the Japanese source text (step ST5 in Figure 4: YES), the modification reception unit 14 accepts the modification of the source text (step ST6 in Figure 4) and outputs the modified source text to the first translation unit 12. For the sake of clarity, the wording here has been revised to "Please be sure to rotate the zipper after it has been installed to confirm that it is working correctly." If the user does not perform an operation to modify the original Japanese text (in the case of step ST5:NO in Figure 4), the modification reception unit 14 will not accept the modification of the original text.

[0027] The first translation unit 12 retrieves the revised original text when the revised original text is output from the revision reception unit 14. The first translation unit 12 provides the revised source text to the translation engine 2 and obtains the English translation from the translation engine 2. The first translation unit 12 outputs the English translation to the line-wrap translation unit 13 and the display processing unit 16, respectively.

[0028] The return translation unit 13 retrieves the English translation from the first translation unit 12. The wrap-around translation unit 13 provides the English translation to the translation engine 2 and retrieves the wrap-around translation from the translation engine 2. The wrap-around translation unit 13 outputs the wrap-around translated text to the display processing unit 16. If the English translation of the above-corrected original text is given to translation engine 2, translation engine 2 may output a line-wrapped translation such as, "After installation, be sure to turn the fasteners and check thoroughly." The nuance of this translated response matches that of the original text, and there is no need to revise the original text further. The display processing unit 16 displays the re-translated text output from the correction reception unit 14 on the display device 3 (step ST4 in Figure 4).

[0029] After reviewing the translated text, if the user recognizes any nuances between the corrected original text and the translated text, they can modify the original Japanese text by operating the correction reception unit 14. If the user performs an operation to further modify the original text after the modification (step ST5 in Figure 4: YES), the modification reception unit 14 accepts the modification of the original text (step ST6 in Figure 4) and outputs the modified original text to the first translation unit 12. If the user does not perform any further modifications to the original text after the modifications (in the case of step ST5:NO in Figure 4), the modification acceptance unit 14 will not accept the modifications to the original text. If the original text has been revised at least once, the revision receiving unit 14 outputs the last revised original text to the second translation unit 15.

[0030] The second translation unit 15 retrieves either the original text that was last corrected by the correction acceptance unit 14, or the original Japanese text retrieved by the original text retrieval unit 11. The second translation unit 15 translates one of the acquired source texts into the second language, Portuguese (step ST7 in Figure 4). Specifically, the second translation unit 15 provides one of the acquired source texts to the translation engine 2 and obtains a Portuguese translation from the translation engine 2. The second translation unit 15 outputs the translated text in the second language to the display processing unit 16.

[0031] When the Japanese source text obtained by the source text acquisition unit 11 is given to the translation engine 2, the translation engine 2 may output a Portuguese translation such as, for example, "Again, after installation, be sure to turn the zipper and check." The nuance of this Portuguese translation matches that of the original text, and there is no need to revise the original.

[0032] The display processing unit 16 displays the Portuguese translation output from the second translation unit 15 on the display device 3.

[0033] In the above embodiment 1, the translation device 1 is configured to include a source text acquisition unit 11 that acquires the source text to be translated, a first translation unit 12 that translates the source text acquired by the source text acquisition unit 11 into a first language, a reverse translation unit 13 that reverses the translation of the text by the first translation unit 12, a display processing unit 16 that displays the reversed translation of the text by the reversed translation unit 13 on the display device 3, and a correction acceptance unit 14 that accepts corrections to the source text after the reversed translation of the text has been displayed by the display processing unit 16. Furthermore, when a correction to the source text is accepted by the correction acceptance unit 14, the translation device 1 includes a second translation unit 15 that translates the corrected source text accepted by the correction acceptance unit 14 into a second language.Therefore, the translation device 1 can translate the source text to be translated into multiple languages ​​and can reduce the time required for translation into multiple languages. The reason why the time required for translation can be reduced in this way is that after the display processing unit 16 displays the line-wrapped translation, the correction reception unit 14 accepts the correction of the original text, and the second translation unit 15 translates the corrected original text accepted by the correction reception unit 14 into the second language. Therefore, the translation into the second language can be performed with content that reflects the translation result into the first language. For example, if the original text uses the user's native language, the original text may contain a mix of colloquial and formal expressions, resulting in sentences that are understandable to native speakers but grammatically ambiguous. For this reason, it is generally considered difficult to translate the original text into a correct translation in a single translation operation, and it becomes necessary to correct the original text. Translation device 1 translates the source text into the first language, displays the translated text, and then the user reviews the translated text and corrects the source text. The corrected source text is then used to translate into the second language. Because the translation into the second language is performed using the corrected, already easily translatable source text, a higher accuracy translation can be obtained in a shorter time than before. Furthermore, even if, for example, the similarity between the grammar of the first language and the grammar of the second language is higher than the similarity between the grammar of the language used in the source text and the grammar of the first language, the translation device 1 performs the translation into the second language using the source text that the user has reviewed and corrected, thus enabling a translation with higher accuracy than before to be obtained in a shorter time.

[0034] In the translation system shown in Figure 1, the wrap-around translation unit 13 wraps the English translation from the first translation unit 12. The wrap-around translation unit 13 may also wrap the Portuguese translation from the second translation unit 15. In this case, the display processing unit 16 may display the wrapped translation related to the Portuguese translation on the display device 3, after which the correction acceptance unit 14 may accept corrections to the original text.

[0035] Embodiment 2. Embodiment 2 describes a translation device 1 in which the second translation unit 17 causes either the revised source text received by the revision receiving unit 14 or the source text acquired by the source text acquisition unit 11 to be translated into one or more languages ​​different from the first language and the second language, respectively.

[0036] Figure 5 is a configuration diagram showing a translation system including the translation device 1 according to Embodiment 2. In Figure 5, the same reference numerals as in Figure 1 indicate the same or corresponding parts, so a detailed explanation is omitted. Figure 6 is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 2. In Figure 6, the same reference numerals as in Figure 2 indicate the same or corresponding parts, so a detailed explanation is omitted. The translation system shown in Figure 5 comprises a translation device 1, a translation engine 2, and a display device 3. The translation device 1 shown in Figure 5 comprises a source text acquisition unit 11, a first translation unit 12, a reverse translation unit 13, a correction acceptance unit 14, a second translation unit 17, and a display processing unit 16.

[0037] The second translation unit 17 is implemented, for example, by the second translation circuit 27 shown in Figure 6. The second translation unit 17 retrieves the revised original text from the revision acceptance unit 14 if the revisions have been accepted by the revision acceptance unit 14. The second translation unit 17 retrieves the original Japanese text from the original text retrieval unit 11 if no revisions have been accepted by the revision acceptance unit 14. The second translation unit 17, if the revisions have been accepted by the revision acceptance unit 14, will translate the revised source text accepted by the revision acceptance unit 14 into the second language, and will also translate the revised source text into one or more languages ​​different from both the first and second languages. The second translation unit 17, if no revisions have been accepted by the revision acceptance unit 14, will translate the source text obtained by the source text acquisition unit 11 into the second language, and will also translate the source text into one or more languages ​​different from both the first and second languages. Specifically, the second translation unit 17 provides the translation engine 2 with either the revised source text received by the revision acceptance unit 14 or the source text acquired by the source text acquisition unit 11, and obtains a translation in the second language from the translation engine 2, as well as translations in one or more languages ​​different from the first language and the second language. The second translation unit 17 outputs the translated text in the second language and the translated text in one or more languages ​​different from the first language and the second language to the display processing unit 16.

[0038] In Figure 5, it is assumed that each of the components of the translation device 1—the source text acquisition unit 11, the first translation unit 12, the reverse translation unit 13, the correction acceptance unit 14, the second translation unit 17, and the display processing unit 16—is implemented by dedicated hardware as shown in Figure 6. Specifically, it is assumed that the translation device 1 is implemented by the source text acquisition circuit 21, the first translation circuit 22, the reverse translation circuit 23, the correction acceptance circuit 24, the second translation circuit 27, and the display processing circuit 26. Each of the source text acquisition circuit 21, the first translation circuit 22, the reverse translation circuit 23, the correction acceptance circuit 24, the second translation circuit 27, and the display processing circuit 26 can be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

[0039] The components of the translation device 1 are not limited to those implemented by dedicated hardware; the translation device 1 may also be implemented by software, firmware, or a combination of software and firmware. If the translation device 1 is implemented by software or firmware, a program is stored in memory 31 that causes the computer to execute the respective processing procedures in the source text acquisition unit 11, the first translation unit 12, the reverse translation unit 13, the correction acceptance unit 14, the second translation unit 17, and the display processing unit 16. The computer's processor 32 then executes the program stored in memory 31.

[0040] Furthermore, Figure 6 shows an example in which each component of the translation device 1 is implemented by dedicated hardware, while Figure 3 shows an example in which the translation device 1 is implemented by software or firmware, etc. However, this is merely one example, and some components of the translation device 1 may be implemented by dedicated hardware, while the remaining components may be implemented by software or firmware, etc.

[0041] Next, we will explain the operation of the translation system shown in Figure 5. The second translation unit 17 retrieves the revised original text from the revision acceptance unit 14 if the revisions have been accepted by the revision acceptance unit 14. If the revision reception unit 14 has revised the original text one or more times, the second translation unit 17 obtains the original text that was last revised by the revision reception unit 14 as the revised original text. The second translation unit 17 retrieves the original Japanese text from the original text retrieval unit 11 if no revisions have been accepted by the revision acceptance unit 14. If the revisions have been accepted by the revision acceptance unit 14, the second translation unit 17 will translate the revised source text accepted by the revision acceptance unit 14 into the second language, similar to the second translation unit 15 shown in Figure 1. Furthermore, the second translation unit 17 translates the revised source text received by the revision reception unit 14 into one or more languages ​​different from the first and second languages. Examples of one or more languages ​​different from the first and second languages ​​include Spanish, German, Italian, Chinese, Korean, or Tagalog.

[0042] If no revisions have been accepted by the revision acceptance unit 14, the second translation unit 17 will translate the source text acquired by the source text acquisition unit 11 into the second language, similar to the second translation unit 15 shown in Figure 1. Furthermore, the second translation unit 17 translates the source text obtained by the source text acquisition unit 11 into one or more languages ​​different from the first language and the second language. The second translation unit 17 outputs the translated text in the second language and the translated text in one or more languages ​​different from the first language and the second language to the display processing unit 16.

[0043] The display processing unit 16 displays the source text to be translated, output from the source text acquisition unit 11, on the display device 3. The display processing unit 16 displays the English translation output from the first translation unit 12 on the display device 3. The display processing unit 16 displays the reversed translation output from the reversed translation unit 13 on the display device 3. The display processing unit 16 displays the Portuguese translation output from the second translation unit 15 on the display device 3. Furthermore, the display processing unit 16 causes the display device 3 to display the translated text in one or more languages ​​different from the first language and the second language, which is output from the second translation unit 15.

[0044] In the above embodiment 2, the translation device 1 is configured such that the second translation unit 17 translates either the revised source text received by the revision reception unit 14 or the source text obtained by the source text acquisition unit 11 into the second language, and also translates either the revised source text received by the revision reception unit 14 or the source text obtained by the source text acquisition unit 11 into one or more languages ​​different from the first language and the second language. Therefore, the translation device 1 can reduce mistranslations when translating the source text to be translated into multiple languages.

[0045] Embodiment 3. Embodiment 3 describes a translation device 1 that includes a first translation unit 41 that, if a term contained in the source text acquired by the source text acquisition unit 11 is a technical term recorded in a technical term dictionary, acquires translation information corresponding to the term contained in the source text from the technical term dictionary and uses the translation information to translate the term contained in the source text into a first language.

[0046] Figure 7 is a configuration diagram showing a translation system including the translation device 1 according to Embodiment 3. In Figure 7, the same reference numerals as in Figures 1 and 5 indicate the same or corresponding parts, so a detailed explanation is omitted. Figure 8 is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 3. In Figure 8, the same reference numerals as in Figures 2 and 6 indicate the same or corresponding parts, so a detailed explanation is omitted. The translation system shown in Figure 7 comprises a translation device 1, a translation engine 4, and a display device 3. The translation device 1 shown in Figure 7 comprises a source text acquisition unit 11, a first translation unit 41, a reverse translation unit 42, a correction acceptance unit 14, a second translation unit 43, and a display processing unit 16.

[0047] Similar to translation engine 2 shown in Figure 1, translation engine 4, upon receiving the source text to be translated from translation device 1, translates the source text into each language and outputs the translated text in each language to translation device 1. Unlike translation engine 2 shown in Figure 1, translation engine 4 is equipped with a specialized terminology dictionary that records the correspondence between specialized terms and their translation information. When translation engine 4 translates the source text into, for example, a first language, it refers to a specialized terminology dictionary. If a term contained in the source text is a specialized term recorded in the specialized terminology dictionary, it retrieves translation information corresponding to that term from the dictionary and uses that translation information to translate the term into the first language.

[0048] The first translation unit 41 is implemented, for example, by the first translation circuit 51 shown in Figure 8. The first translation unit 41 retrieves the source text to be translated from the source text retrieval unit 11. The first translation unit 41, similar to the first translation unit 12 shown in Figure 1, translates the source text obtained by the source text acquisition unit 11 into the first language. The first translation unit 41, when translating the source text obtained by the source text acquisition unit 11 into the first language, refers to a specialized terminology dictionary. If a term contained in the source text is a specialized term recorded in the specialized terminology dictionary, it obtains translation information corresponding to the term contained in the source text from the specialized terminology dictionary and uses the translation information to translate the term contained in the source text into the first language. In the translation system shown in Figure 7, the translation engine 4 is located outside the translation device 1. However, this is just one example, and the translation engine 4 may also be located inside the translation device 1. For example, if the first translation unit 41 is equipped with the translation engine 4, the first translation unit 41 translates the source text acquired by the source text acquisition unit 11 into the first language. The first translation unit 41 outputs the translated text in the first language to the line-reversal translation unit 42 and the display processing unit 16, respectively.

[0049] The reverse translation unit 42 is implemented, for example, by the reverse translation circuit 52 shown in Figure 8. The return translation unit 42 obtains the translated text in the first language from the first translation unit 41. The reverse translation unit 42 reverses the translation of the text produced by the first translation unit 41. Specifically, the wrap-around translation unit 42 provides the translation of the first language to the translation engine 4 and obtains the wrap-around translation from the translation engine 4. The reverse translation unit 42, if the terms contained in the source text obtained by the source text acquisition unit 11 by the first translation unit 41 have been translated using translation information obtained from a specialized terminology dictionary, refers to the correspondence between the terms contained in the source text and the translation information and causes the first translation unit 41 to reverse translate the text. The wrap-around translation unit 42 outputs the wrap-around translated text to the display processing unit 16.

[0050] The second translation unit 43 is implemented, for example, by the second translation circuit 53 shown in Figure 8. The second translation unit 43 retrieves the revised original text from the revision acceptance unit 14 if the revisions have been accepted by the revision acceptance unit 14. The second translation unit 43 retrieves the original Japanese text from the original text retrieval unit 11 if no revisions have been accepted by the revision acceptance unit 14. The second translation unit 43, if a revision has been accepted by the revision acceptance unit 14, will translate the revised source text accepted by the revision acceptance unit 14 into the second language; if the revision has not been accepted by the revision acceptance unit 14, it will translate the source text acquired by the source text acquisition unit 11 into the second language. Specifically, the second translation unit 43 provides the translation engine 4 with either the revised source text received by the revision acceptance unit 14 or the source text acquired by the source text acquisition unit 11, and obtains a translation in the second language from the translation engine 4. When the second translation unit 43 translates either the revised source text received by the revision reception unit 14 or the source text obtained by the source text acquisition unit 11 into a second language, if the first translation unit 41 has translated the terms contained in the source text obtained by the source text acquisition unit 11 using translation information obtained from a specialized terminology dictionary, the second translation unit 43 uses the translation information to translate the terms contained in the revised source text received by the revision reception unit 14 or the terms contained in the source text obtained by the source text acquisition unit 11 into the second language. The second translation unit 43 outputs the translated text in the second language to the display processing unit 16.

[0051] In the translation system shown in Figure 7, the first translation unit 41, the reverse translation unit 42, and the second translation unit 43 are each applied to the translation device 1 shown in Figure 1. However, this is merely one example, and the first translation unit 41, the reverse translation unit 42, and the second translation unit 43 may also be applied to the translation device 1 shown in Figure 5.

[0052] In Figure 7, it is assumed that each of the components of the translation device 1—the source text acquisition unit 11, the first translation unit 41, the reverse translation unit 42, the correction acceptance unit 14, the second translation unit 43, and the display processing unit 16—is implemented by dedicated hardware as shown in Figure 8. That is, it is assumed that the translation device 1 is implemented by the source text acquisition circuit 21, the first translation circuit 51, the reverse translation circuit 52, the correction acceptance circuit 24, the second translation circuit 53, and the display processing circuit 26. Each of the source text acquisition circuit 21, the first translation circuit 51, the reverse translation circuit 52, the correction acceptance circuit 24, the second translation circuit 53, and the display processing circuit 26 can be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

[0053] The components of the translation device 1 are not limited to those implemented by dedicated hardware; the translation device 1 may also be implemented by software, firmware, or a combination of software and firmware. If the translation device 1 is implemented by software or firmware, a program that causes a computer to execute the respective processing procedures in the source text acquisition unit 11, the first translation unit 41, the reverse translation unit 42, the correction acceptance unit 14, the second translation unit 43, and the display processing unit 16 is stored in the memory 31 shown in Figure 3. Then, the processor 32 shown in Figure 3 executes the program stored in the memory 31.

[0054] Furthermore, Figure 8 shows an example in which each component of the translation device 1 is implemented by dedicated hardware, while Figure 3 shows an example in which the translation device 1 is implemented by software or firmware, etc. However, this is merely one example, and some components of the translation device 1 may be implemented by dedicated hardware, while the remaining components may be implemented by software or firmware, etc.

[0055] Next, we will explain the operation of the translation system shown in Figure 7. Except for the translation engine 4, the first translation unit 41, the wrap-around translation unit 42, and the second translation unit 43, the system is the same as the translation system shown in Figure 1. Therefore, this section will mainly describe the operation of the translation engine 4, the first translation unit 41, the wrap-around translation unit 42, and the second translation unit 43.

[0056] As shown in Figure 9, the translation engine 4 includes a specialized terminology dictionary in which the correspondence between specialized terms and their translation information is recorded. Examples of translation information include information showing the pronunciation of technical terms and information showing the translation of technical terms in the first language. Figure 9 is an explanatory diagram showing an example of a technical term recorded in a technical term dictionary, its definition, its pronunciation, and a translation of the technical term into a first language. The technical terms recorded in a technical glossary include not only so-called technical terms but also, for example, company-specific jargon. Technical terms are, for example, terms used by people engaged in a particular occupation, or terms used only in a particular field of study or industry. In the example in Figure 9, the following technical terms are recorded: "Advanced Research Institute," "Information Research Institute," "IS Building," "M Seminar," and "Regular Departure Date." The definitions of technical terms are displayed on the display device 3 by the display processing unit 16, for example, as annotations to the original text when the original text to be translated is displayed on the display device 3. For example, the definition of "Advanced Research Institute" is "Advanced Technology Research Institute," and the definition of "M Seminar" is "MELCO Seminar." For example, the pronunciation of "Jouhou Souken" is "Joho-Soken", and the pronunciation of "IS Building" is "IS-Tou". For example, the first language translation of "M Seminar" is "MELCO Seminar", and the first language translation of "Teitai Hi" is "Regular Closing Day".

[0057] The first translation unit 41 acquires the original text to be translated from the original text acquisition unit 11. The first translation unit 41 supplies the original text acquired by the original text acquisition unit 11 to the translation engine 4, and causes the translation engine 4 to translate the original text into the first language. When causing the original text acquired by the original text acquisition unit 11 to be translated into the first language, if a term included in the original text is a technical term recorded in a technical term dictionary, the first translation unit 41 causes the term included in the original text to be translated into the first language by using translation information corresponding to the term included in the original text.

[0058] When the original text is supplied from the first translation unit 41, the translation engine 4 extracts terms included in the original text, and checks whether or not the extracted terms are technical terms recorded in the technical term dictionary. If none of the terms included in the original text include any technical term recorded in the technical term dictionary, the translation engine 4 translates the original text into the first language in the same manner as the translation engine 2 shown in FIG. 1, and outputs the translated text in the first language to the first translation unit 41. If any of the terms included in the original text includes a technical term recorded in the technical term dictionary, the translation engine 4 acquires translation information corresponding to the term included in the original text from the technical term dictionary, and translates the term included in the original text into the first language using the translation information. Specifically, when the term included in the original text is, for example, "Teitai Hi", the translation engine 4 translates the term included in the original text into either "Teitaibi", which is the pronunciation of "Teitai Hi", or "Regular Closing Day", which is the first language translation of "Teitai Hi". In addition, when the first translation unit 41 causes terms included in the original text to be translated into the first language, it may include a man-machine interface that accepts a selection of either information indicating the reading of a technical term or information indicating a translation of the technical term in the first language as translation information to be used, so that the user can select either information indicating the reading of a technical term or information indicating a translation in the first language as the translation information. If the translation information selected by the user is information indicating the reading of a technical term, the translation engine 4 translates the term "Teitaibi" included in the original text as "Teitaibi", for example. If the translation information selected by the user is information indicating a translation in the first language, the translation engine 4 translates the term "Teitaibi" included in the original text as "Regular Closing Day", for example.

[0059] The first translation unit 41 outputs the translated text in the first language to each of the back-translation unit 42 and the display processing unit 16. Any method may be used for the confirmation processing of whether a term included in the original text is a technical term recorded in a technical term dictionary. For example, the translation engine 4 may provide the original text to generative AI (Artificial Intelligence), and the generative AI may determine whether the term included in the original text is a technical term recorded in the technical term dictionary.

[0060] The back-translation unit 42 acquires the translated text in the first language from the first translation unit 41. The back-translation unit 42 causes back-translation of the translated text obtained from the first translation unit 41. Specifically, the back-translation unit 42 provides the translated text in the first language to the translation engine 4, and acquires the back-translated text from the translation engine 4. When translating terms included in an original text into a first language, the translation engine 4 acquires translation information corresponding to the terms included in the original text from a technical term dictionary, and if the terms included in the original text have been translated into the first language using the translation information, back-translates the translated sentence produced by a first translation unit 41 by referring to the correspondence between the terms included in the original text and the translation information. Specifically, when a term included in the original text is, for example, "定退日", and the term "定退日" has been translated into either "Teitaibi" or "Regular Closing Day", the translation engine 4 back-translates either "Teitaibi" or "Regular Closing Day" back to "定退日" by referring to the correspondence between the terms included in the original text and the translation information. A back-translation unit 42 outputs the back-translated sentence to a display processing unit 16.

[0061] A second translation unit 43 acquires the corrected original text from a correction accepting unit 14 if correction has been accepted by the correction accepting unit 14. The second translation unit 43 acquires the Japanese original text from an original text acquisition unit 11 if no correction has been accepted by the correction accepting unit 14. The second translation unit 43 causes the corrected original text accepted by the correction accepting unit 14 to be translated into a second language if correction has been accepted by the correction accepting unit 14, and causes the original text acquired by the original text acquisition unit 11 to be translated into the second language if no correction has been accepted by the correction accepting unit 14.

[0062] Specifically, the second translation unit 43 provides either the corrected original text accepted by the correction accepting unit 14 or the original text acquired by the original text acquisition unit 11 to the translation engine 4, and acquires a translated sentence in the second language from the translation engine 4. When translating a term included in the original text into the first language, the translation engine 4 acquires translation information corresponding to the term included in the original text from the technical term dictionary, and if the term included in the original text has been translated into the first language using the translation information, the translation engine 4 translates, into the second language, either the term included in the corrected original text accepted by the correction accepting unit 14 or the term included in the original text acquired by the original text acquiring unit 11, using the translation information. If the term included in the original text is, for example, "定退日 (Teitaibi)", and "定退日" has been translated into either "Teitaibi" or "Regular Closing Day", the translation engine 4 translates either "Teitaibi" or "Regular Closing Day" into the second language. Note that when translating into the second language using information indicating the pronunciation of a technical term such as "Teitaibi", using "Teitaibi" as it is may be regarded as the translation into the second language. Alternatively, translation into the second language may be performed by converting the term into a phonetic character corresponding to the second language that has the same pronunciation as "Teitaibi". As described above, by using information indicating the pronunciation of a technical term or the translation of a technical term in the first language for translating into the second language, accurate multilingual translation can be performed even if the original text includes a technical term. The translation engine 4 outputs the translated text in the second language to a second translation unit 43. When the second translation unit 43 receives the translated text in the second language from the translation engine 4, the second translation unit 43 outputs the translated text in the second language to a display processing unit 16.

[0063] In the above embodiment 3, when the first translation unit 41 translates the source text acquired by the source text acquisition unit 11 into the first language, it refers to a specialized term dictionary that records the correspondence between specialized terms and translation information. If a term included in the source text is a specialized term recorded in the specialized term dictionary, it obtains translation information corresponding to the term included in the source text from the specialized term dictionary and uses the translation information to translate the term included in the source text into the first language. The translation device 1 shown in Figure 7 is configured in this way. Therefore, the translation device 1 shown in Figure 7, like the translation device 1 shown in Figure 1, can translate the source text to be translated into multiple languages ​​and can reduce the time required for translation into multiple languages. The translation device 1 shown in Figure 7 can improve the translation accuracy of the first language when the source text contains specialized terms compared to the translation device 1 shown in Figure 1.

[0064] In Embodiment 3, the translation device 1 shown in Figure 7 is configured such that the re-translation unit 42, if the terms contained in the source text acquired by the source text acquisition unit 11 by the first translation unit 41 have been translated using translation information acquired from a specialized terminology dictionary, refers to the correspondence between the terms contained in the source text and the translation information and performs a re-translation of the text by the first translation unit 41. Therefore, the translation device 1 shown in Figure 7 can obtain a correct re-translated text even if the source text contains specialized terminology.

[0065] In Embodiment 3, when the second translation unit 43 translates the revised source text received by the revision reception unit 14 into the second language, if the terms contained in the source text acquired by the source text acquisition unit 11 by the first translation unit 41 have been translated using translation information obtained from a specialized terminology dictionary, the translation device 1 shown in Figure 7 is configured to use this translation information to translate the terms contained in the source text into the second language. Therefore, the translation device 1 shown in Figure 7 can improve the translation accuracy of the second language when the source text contains specialized terminology compared to the translation device 1 shown in Figure 1.

[0066] Embodiment 4. Embodiment 4 describes a translation device 1 that includes a corresponding language identification unit 44 that identifies the corresponding language of the person to whom the translated text by the second translation unit 45 is provided as the second language.

[0067] Figure 10 is a configuration diagram showing a translation system including a translation device 1 according to Embodiment 4. In Figure 10, the same reference numerals as in Figures 1, 5, and 7 indicate the same or corresponding parts, so a detailed explanation is omitted. Figure 11 is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 4. In Figure 11, the same reference numerals as in Figures 2, 6, and 8 indicate the same or corresponding parts, so a detailed explanation is omitted. The translation system shown in Figure 10 comprises a translation device 1, a translation engine 2, and a display device 3. The translation device 1 shown in Figure 10 comprises a source text acquisition unit 11, a first translation unit 12, a reverse translation unit 13, a correction acceptance unit 14, a corresponding language identification unit 44, a second translation unit 45, and a display processing unit 16.

[0068] The language identification unit 44 is implemented, for example, by the language identification circuit 54 shown in Figure 11. The language identification unit 44 identifies the target user's language as the second language. Specifically, the language identification unit 44 identifies the language of the person being addressed based on image information showing the image of the person being addressed. Alternatively, the language identification unit 44 identifies the target person's language based on voice information indicating the target person's voice. The language identification unit 44 outputs the language identification result to the second translation unit 45.

[0069] The second translation unit 45 is implemented, for example, by the second translation circuit 55 shown in Figure 11. The second translation unit 45 obtains the corresponding language identification result from the corresponding language identification unit 44. The second translation unit 45 retrieves the revised original text from the revision acceptance unit 14 if the revisions have been accepted by the revision acceptance unit 14. The second translation unit 45 retrieves the original Japanese text from the original text retrieval unit 11 if no revisions have been accepted by the revision acceptance unit 14. The second translation unit 45, if the revisions have been accepted by the revision acceptance unit 14, will translate the revised source text accepted by the revision acceptance unit 14 into the target language of the recipient. If the revisions have not been accepted by the revision acceptance unit 14, it will translate the source text acquired by the source text acquisition unit 11 into the target language of the recipient. The second translation unit 45 outputs the translated text in the second language, which is the language of the target recipient, to the display processing unit 16.

[0070] In the translation system shown in Figure 10, the corresponding language identification unit 44 and the second translation unit 45 are applied to the translation device 1 shown in Figure 1. However, this is merely one example, and the corresponding language identification unit 44 and the second translation unit 45 may also be applied to the translation device 1 shown in Figure 5 or the translation device 1 shown in Figure 7.

[0071] In Figure 10, it is assumed that each of the components of the translation device 1—the source text acquisition unit 11, the first translation unit 12, the reverse translation unit 13, the correction acceptance unit 14, the corresponding language identification unit 44, the second translation unit 45, and the display processing unit 16—is implemented by dedicated hardware as shown in Figure 11. That is, it is assumed that the translation device 1 is implemented by the source text acquisition circuit 21, the first translation circuit 22, the reverse translation circuit 23, the correction acceptance circuit 24, the corresponding language identification circuit 54, the second translation circuit 55, and the display processing circuit 26. Each of the source text acquisition circuit 21, the first translation circuit 22, the reverse translation circuit 23, the correction acceptance circuit 24, the corresponding language identification circuit 54, the second translation circuit 55, and the display processing circuit 26 can be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

[0072] The components of the translation device 1 are not limited to those implemented by dedicated hardware; the translation device 1 may also be implemented by software, firmware, or a combination of software and firmware. If the translation device 1 is implemented by software or firmware, a program that causes a computer to execute the respective processing procedures in the source text acquisition unit 11, the first translation unit 12, the reverse translation unit 13, the correction acceptance unit 14, the corresponding language identification unit 44, the second translation unit 45, and the display processing unit 16 is stored in the memory 31 shown in Figure 3. Then, the processor 32 shown in Figure 3 executes the program stored in the memory 31.

[0073] Furthermore, Figure 11 shows an example in which each component of the translation device 1 is implemented by dedicated hardware, and Figure 3 shows an example in which the translation device 1 is implemented by software or firmware, etc. However, this is only one example, and some components of the translation device 1 may be implemented by dedicated hardware, while the remaining components may be implemented by software or firmware, etc.

[0074] Next, the operation of the translation system shown in Figure 10 will be described. Except for the corresponding language identification unit 44 and the second translation unit 45, it is the same as the translation system shown in Figure 1. Therefore, only the operation of the corresponding language identification unit 44 and the second translation unit 45 will be described here.

[0075] Figure 12 is an explanatory diagram showing an example of an image in which the recipient of the information is pictured. As shown in Figure 12, the language identification unit 44 acquires image information indicating an image in which the target person is pictured. The language identification unit 44 identifies the language of the person to be provided by performing facial recognition processing on the person shown in the image indicated by the image information. Specifically, if a table is provided that records the facial images of multiple recipients and the corresponding languages ​​of each recipient, the corresponding language identification unit 44 will compare the facial image of the recipient shown in the image indicated by the image information with the facial images of the multiple recipients recorded in the table. The corresponding language identification unit 44 then identifies a facial image among the multiple facial images of recipients recorded in the table that matches the facial image of the recipient shown in the image indicated by the image information. The language identification unit 44 obtains the language of the person to whom the identified facial image is provided from the table. The language identification unit 44 may also identify the language of each recipient if multiple recipients are shown in the image. The language identification unit 44 outputs the identification result of the target user's language to the second translation unit 45.

[0076] Here, the language identification unit 44 identifies the target person's supported language by performing facial recognition processing on the target person. However, this is just one example, and the language identification unit 44 may also provide image information showing an image of the target person to the generating AI and obtain the identification result of the target person's supported language from the generating AI. In this case, the language identification unit 44 may also perform authentication processing other than facial recognition, such as fingerprint authentication processing, palm print authentication processing, vein authentication processing, iris authentication processing, or ear print authentication processing. Alternatively, the language identification unit 44 may acquire voice information indicating the voice of the person to be served and identify the person's language by analyzing the language of the voice indicated by the voice information. In this case, the language identification unit 44 may provide the voice information to a generating AI and obtain the identification result of the person's language from the generating AI.

[0077] The second translation unit 45 obtains the corresponding language identification result from the corresponding language identification unit 44 and determines the corresponding language to be the second language. The second translation unit 45 retrieves the revised original text from the revision acceptance unit 14 if the revisions have been accepted by the revision acceptance unit 14. The second translation unit 45 retrieves the original Japanese text from the original text retrieval unit 11 if no revisions have been accepted by the revision acceptance unit 14. If the revisions have been accepted by the revision acceptance unit 14, the second translation unit 45 will translate the revised source text accepted by the revision acceptance unit 14 into the second language, similar to the second translation unit 15 shown in Figure 1. If no revisions have been accepted by the revision acceptance unit 14, the second translation unit 45 will translate the source text acquired by the source text acquisition unit 11 into the second language, similar to the second translation unit 15 shown in Figure 1. The second translation unit 45 outputs the translated text in the second language to the display processing unit 16.

[0078] In the above embodiment 4, the translation device 1 shown in Figure 10 is configured such that the second translation unit 45 includes a corresponding language identification unit 44 that identifies the corresponding language of the recipient, who is the person to whom the translated text is provided, as the second language, and the second translation unit 45 causes the revised source text received by the revision reception unit 14 to be translated into the corresponding language identified by the corresponding language identification unit 44. Therefore, the translation device 1 shown in Figure 10, like the translation device 1 shown in Figure 1, can translate the source text to be translated into multiple languages, reduce the time required for translation into multiple languages, and can automatically set the recipient's corresponding language as the second language.

[0079] In the translation device 1 shown in Figure 10, the language identification unit 44 identifies the target language of the person receiving the translation as the second language. If there is an error in the identification result of the target language, the language identification unit 44 may be equipped with a human-machine interface that accepts corrections to the identification result of the target language. In this case, if the user corrects the identification result of the language identification unit 44, the correct language can be determined as the second language even if the identification result of the language identification unit 44 is incorrect.

[0080] Embodiment 5. Embodiment 5 describes a translation device 1 comprising a first revised text acquisition unit 46 that provides the source text acquired by the source text acquisition unit 11 to the generation AI and obtains a revised version of the source text from the generation AI, and a second revised text acquisition unit 47 that provides the reversed translation text from the reversed translation unit 13 to the generation AI and obtains a revised version of the reversed translation text from the generation AI.

[0081] Figure 13 is a configuration diagram showing a translation system including a translation device 1 according to Embodiment 5. In Figure 13, the same reference numerals as in Figures 1, 5, 7, and 10 indicate the same or corresponding parts, so a detailed explanation is omitted. Figure 14 is a hardware configuration diagram showing the hardware of the translation device 1 according to Embodiment 5. In Figure 14, the same reference numerals as in Figures 2, 6, 8, and 11 indicate the same or corresponding parts, so a detailed explanation is omitted. The translation system shown in Figure 13 comprises a translation device 1, a translation engine 2, and a display device 3. The translation device 1 shown in Figure 13 comprises a source text acquisition unit 11, a first revised text acquisition unit 46, a first translation unit 12, a reverse translation unit 13, a second revised text acquisition unit 47, a revision reception unit 14, a second translation unit 45, and a display processing unit 16.

[0082] The first modified text acquisition unit 46 is implemented, for example, by the first modified text acquisition circuit 56 shown in Figure 14. The first revised text acquisition unit 46 provides the original text acquired by the original text acquisition unit 11 to the generation AI, and obtains a revised version of the original text from the generation AI. The first revised text acquisition unit 46 outputs the revised text of the original text to the first translation unit 12, the revision reception unit 14, the second translation unit 15, and the display processing unit 16, respectively.

[0083] The second correction statement acquisition unit 47 is implemented, for example, by the second correction statement acquisition circuit 57 shown in Figure 14. The second revised text acquisition unit 47 provides the reversed translation text from the reversed translation unit 13 to the generation AI, and obtains the revised version of the reversed translation text from the generation AI. The second correction text acquisition unit 47 outputs the corrected text of the line-reversed translation to the display processing unit 16.

[0084] The translation device 1 shown in Figure 13 includes both a first revised text acquisition unit 46 and a second revised text acquisition unit 47. However, this is merely an example, and the translation device 1 may include either the first revised text acquisition unit 46 or the second revised text acquisition unit 47.

[0085] In the translation system shown in Figure 13, the first revised text acquisition unit 46 and the second revised text acquisition unit 47 are applied to the translation device 1 shown in Figure 1. However, this is merely one example, and the first revised text acquisition unit 46 and the second revised text acquisition unit 47 may be applied to the translation device 1 shown in Figure 5, the translation device 1 shown in Figure 7, or the translation device 1 shown in Figure 10.

[0086] Figure 13 assumes that each of the components of the translation device 1—the source text acquisition unit 11, the first revised text acquisition unit 46, the first translation unit 12, the reverse translation unit 13, the second revised text acquisition unit 47, the revision reception unit 14, the second translation unit 15, and the display processing unit 16—is implemented by dedicated hardware as shown in Figure 14. Specifically, the translation device 1 is assumed to be implemented by the source text acquisition circuit 21, the first revised text acquisition circuit 56, the first translation circuit 22, the reverse translation circuit 23, the second revised text acquisition circuit 57, the revision reception circuit 24, the second translation circuit 25, and the display processing circuit 26. Each of the original text acquisition circuit 21, the first revised text acquisition circuit 56, the first translation circuit 22, the reverse translation circuit 23, the second revised text acquisition circuit 57, the revision acceptance circuit 24, the second translation circuit 25, and the display processing circuit 26 can be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

[0087] The components of the translation device 1 are not limited to those implemented by dedicated hardware; the translation device 1 may also be implemented by software, firmware, or a combination of software and firmware. When the translation device 1 is implemented by software or firmware, a program is stored in the memory 31 shown in Figure 3 that causes a computer to execute the respective processing procedures in the source text acquisition unit 11, the first revised text acquisition unit 46, the first translation unit 12, the reverse translation unit 13, the second revised text acquisition unit 47, the revision reception unit 14, the second translation unit 15, and the display processing unit 16. Then, the processor 32 shown in Figure 3 executes the program stored in the memory 31.

[0088] Furthermore, Figure 14 shows an example in which each component of the translation device 1 is implemented by dedicated hardware, and Figure 3 shows an example in which the translation device 1 is implemented by software or firmware, etc. However, this is only one example, and some components of the translation device 1 may be implemented by dedicated hardware, while the remaining components may be implemented by software or firmware, etc.

[0089] Next, the operation of the translation system shown in Figure 13 will be described. Except for the first revised text acquisition unit 46 and the second revised text acquisition unit 47, it is the same as the translation system shown in Figure 1. Therefore, here we will mainly describe the operation of the first revised text acquisition unit 46 and the second revised text acquisition unit 47. Figure 15 is a flowchart showing the translation method, which is the processing procedure of the translation device 1. In Figure 15, steps identical to those in Figure 4 are shown in the same or equivalent parts, so a detailed explanation is omitted.

[0090] The source text acquisition unit 11 acquires the Japanese source text as the source text to be translated (step ST1 in Figure 15). For the sake of explanation, we will assume that the original Japanese text obtained here is: "Yesterday, a reassessment was required on the ENG-5678 model production line due to incorrect part installation. Please be careful to avoid assembly errors and other mistakes on a daily basis." The original text acquisition unit 11 outputs the original Japanese text to the first revised text acquisition unit 46 and the display processing unit 16, respectively. The display processing unit 16 displays the original Japanese text, "Yesterday, a review was required on the ENG-5678 model manufacturing line due to incorrect part installation. Please be careful to avoid assembly errors and other mistakes on a daily basis," on the display device 3.

[0091] The first revised text acquisition unit 46 acquires the original Japanese text from the original text acquisition unit 11. The first revised text acquisition unit 46 is equipped with a human-machine interface such as a microphone. If the user wants the original Japanese text to be converted into beautiful Japanese, for example, they provide the first revised text acquisition unit 46 with a voice prompt to the generating AI, such as "Please convert this into beautiful Japanese." The first revised text acquisition unit 46, when given the above prompt, provides the Japanese source text to the generation AI along with the above prompt. If no prompt is given, the first revised text acquisition unit 46 outputs the original Japanese text to the first translation unit 12, the revision acceptance unit 14, the second translation unit 15, and the display processing unit 16, respectively.

[0092] When the generation AI receives the above prompt and the original Japanese text from the first revised text acquisition unit 46, it converts the original Japanese text into fluent Japanese and outputs the converted text as the revised original text to the first revised text acquisition unit 46. The process of revising the original text by the generation AI is a well-known technique, so a detailed explanation is omitted. The first revised text acquisition unit 46 acquires the revised text of the original text from the generating AI (step ST11 in Figure 15). Here, the generating AI outputs the following as a corrected version of the original text to the first corrected text acquisition unit 46: "On the ENG-5678 model manufacturing line yesterday, a review was required due to the installation of the wrong parts. Please be careful to avoid assembly errors and other mistakes on a daily basis." The first revised text acquisition unit 46 outputs the revised text of the original text to the first translation unit 12, the revision reception unit 14, the second translation unit 15, and the display processing unit 16, respectively. The display processing unit 16 displays the corrected version of the original text, "Yesterday, a review was required on the ENG-5678 model manufacturing line due to an error in the installation of parts. Please be careful to avoid assembly errors and other mistakes on a daily basis," on the display device 3.

[0093] In the translation device 1 shown in Figure 13, the first corrected text acquisition unit 46 is shown to be given a voice prompt to the generation AI, for example, saying "Please translate into beautiful Japanese." However, this is just one example. For example, a screen for setting the beautiful Japanese mode to either ON or OFF could be displayed on the display device 3, and if the user sets it to ON, the first corrected text acquisition unit 46 would provide the original Japanese text to the generation AI, causing the generation AI to translate the original text into beautiful Japanese.

[0094] The first translation unit 12 obtains the original Japanese text, or the revised version of the original text, from the first revised text acquisition unit 46. The first translation unit 12 translates the original Japanese text, or a revised version of the original text, into English, which is the first language (step ST2 in Figure 15). Specifically, the first translation unit 12 provides the Japanese source text, or a revised version of the source text, to the translation engine 2, and obtains the English translation from the translation engine 2. The first translation unit 12 outputs the English translation to the line-wrap translation unit 13 and the display processing unit 16, respectively. The display processing unit 16 displays the English translation output from the first translation unit 12 on the display device 3.

[0095] The return translation unit 13 retrieves the English translation from the first translation unit 12. The reverse translation unit 13 reverses the translation of the text by the first translation unit 12 (step ST3 in Figure 15). Specifically, the wrap-around translation unit 13 provides the English translation to the translation engine 2 and retrieves the wrap-around translation from the translation engine 2. The wrap-around translation unit 13 outputs the wrap-around translated text to the second revised text acquisition unit 47.

[0096] The second revised text acquisition unit 47 acquires the wrapped translation text from the wrapped translation unit 13. The second revised text acquisition unit 47 is equipped with a human-machine interface such as a microphone. If the user wants the translated text to be converted into clear Japanese, for example, they provide the second revised text acquisition unit 47 with a voice prompt to the generating AI, such as "Please convert this into clear Japanese." The second corrected text acquisition unit 47, when given the above prompt, provides the line-reversed translation text to the generation AI along with the above prompt. The second correction text acquisition unit 47 outputs the line-wrapped translation to the display processing unit 16 unless the above prompt is given.

[0097] When the generating AI receives the above prompt and the wrapped translation from the second corrected text acquisition unit 47, it converts the wrapped translation into clear Japanese and outputs the converted wrapped translation to the second corrected text acquisition unit 47 as the corrected version of the wrapped translation. The second revised text acquisition unit 47 acquires the revised text of the wrapped translation from the generating AI (step ST12 in Figure 15). The second correction text acquisition unit 47 outputs the corrected text of the line-reversed translation to the display processing unit 16.

[0098] The display processing unit 16 displays the re-translated text output from the second revised text acquisition unit 47, or the revised text of the re-translated text output from the second revised text acquisition unit 47, on the display device 3 (step ST4 in Figure 15).

[0099] After reviewing the translated text, if a user recognizes the difference in nuance between the original Japanese text or the revised original text and the translated text or the revised translated text, they can modify the original Japanese text by operating the modification reception unit 14. If the user performs an operation to further revise the source text (step ST5 in Figure 15: YES), the revision reception unit 14 accepts the revision of the source text (step ST6 in Figure 15) and outputs the revised source text to the first translation unit 12. If the first revision acquisition unit 46 has acquired the revised version of the original text, the original text for which the revision acceptance unit 14 accepts revisions is the revised version of the original text acquired by the first revision acquisition unit 46. If the first revision acquisition unit 46 has not acquired the revised version of the original text, the original text that the revision acceptance unit 14 accepts revisions from is the original text acquired by the original text acquisition unit 11.

[0100] If the user does not perform an operation to further modify the original text after the modification (in the case of step ST5:NO in Figure 15), the modification acceptance unit 14 will not accept the modification of the original text. If the original text has been revised at least once, the revision receiving unit 14 outputs the last revised original text to the second translation unit 15.

[0101] The second translation unit 15 obtains either the original text that was last corrected by the correction acceptance unit 14, the Japanese original text obtained by the original text acquisition unit 11, or the corrected version of the original text obtained by the first correction text acquisition unit 46. The second translation unit 15 translates one of the acquired source texts into the second language, Portuguese (step ST7 in Figure 15). Specifically, the second translation unit 15 provides one of the acquired source texts to the translation engine 2 and obtains a Portuguese translation from the translation engine 2. The second translation unit 15 outputs the translated text in the second language to the display processing unit 16.

[0102] In the above embodiment 5, the translation device 1 shown in Figure 13 is configured such that the original text acquired by the original text acquisition unit 11 is provided to the generation AI, and a first revised text acquisition unit 46 acquires a revised version of the original text from the generation AI, and the first translation unit 12 translates the revised version acquired by the first revised text acquisition unit 46 into the first language instead of the original text acquired by the original text acquisition unit 11. Therefore, the translation device 1 shown in Figure 13 can improve the translation accuracy of the first language compared to the translation device 1 shown in Figure 1.

[0103] In Embodiment 5, the translation device 1 shown in Figure 13 is configured such that the folded translation by the folded translation unit 13 is provided to the generation AI, and a second revised text acquisition unit 47 obtains a revised version of the folded translation from the generation AI, the display processing unit 16 displays the revised version of the folded translation by the second revised text acquisition unit 47 on the display device 3, and the revision reception unit 14 accepts revisions to the original text obtained by the original text acquisition unit 11 or the revised version obtained by the first revised text acquisition unit 46 after the revised version of the folded translation is displayed by the display processing unit 16. Therefore, the translation device 1 shown in Figure 13 can improve the translation accuracy of the second language compared to the translation device 1 shown in Figure 1.

[0104] Embodiment 5 shows an example in which the first revised text acquisition unit 46 or the second revised text acquisition unit 47 prompts the generating AI with "Please convert this into clear Japanese." However, this is only one example, and the first revised text acquisition unit 46, etc., may also provide the generating AI with prompts such as "Please convert this into Japanese that is easy for new employees to understand," or "Please convert this into Japanese that is easy for non-experts to understand," so that the generating AI can acquire a revised text that is appropriate for the level of the target audience. If the target audience includes, for example, new employees or people who are not familiar with the field, the original text can be revised using the above prompts to obtain a revised text that is easy for the target audience to understand.

[0105] Furthermore, the first revised text acquisition unit 46 may acquire information about the recipient and change the prompt based on the recipient's information. The first revised text acquisition unit 46 may, for example, use either the image information or the audio information acquired by the corresponding language identification unit 44 shown in Figure 10 to identify the recipient's attributes and use a prompt corresponding to the identified recipient's attributes to perform revisions that are appropriate for the recipient's level. Specifically, if a table is provided for the target recipients, containing attribute information that indicates the level of the target recipients, such as their year of joining the company or their area of ​​expertise, the first revised text acquisition unit 46, etc., will use either image information or audio information to identify the attributes of the target recipients and obtain prompts from the table that correspond to the attributes of the target recipients. For example, if the target recipient table contains attribute information such as "1st year at the company" and "Level of expertise: low," this information will be used to generate prompts such as "Please translate this into Japanese that is easy for new employees to understand" or "Please translate this into Japanese that is easy for non-experts to understand." This makes it possible to provide text that is tailored to the level of the target recipients.

[0106] Furthermore, this disclosure allows for free combination of each embodiment, modification of any component in each embodiment, or omission of any component in each embodiment. [Industrial applicability]

[0107] This disclosure is suitable for translation devices and translation methods. [Explanation of Symbols]

[0108] 1 Translation device, 2 Translation engine, 3 Display device, 4 Translation engine, 11 Source text acquisition unit, 12 First translation unit, 13 Reverse translation unit, 14 Correction acceptance unit, 15,17 Second translation unit, 16 Display processing unit, 21 Source text acquisition circuit, 22 First translation circuit, 23 Reverse translation circuit, 24 Correction acceptance circuit, 25,27 Second translation circuit, 26 Display processing circuit, 31 Memory, 32 Processor, 41 First translation unit, 42 Reverse translation unit, 43,45 Second translation unit, 44 Corresponding language identification unit, 46 First corrected text acquisition unit, 47 Second corrected text acquisition unit, 51 First translation circuit, 52 Reverse translation circuit, 53,55 Second translation circuit, 54 Corresponding language identification circuit, 56 First corrected text acquisition circuit, 57 Second corrected text acquisition circuit.

Claims

1. The source text acquisition unit obtains the source text to be translated, A first translation unit that translates the source text obtained by the source text acquisition unit into a first language, A wrap-around translation unit that wraps around the translation of the text produced by the first translation unit, A display processing unit that displays the folded translated text by the aforementioned folded translation unit on a display device, After the display processing unit displays the wrapped translation, a correction receiving unit accepts corrections to the original text, The system includes a second translation unit which, upon receiving a revision of the original text from the revision receiving unit, translates the revised original text received by the revision receiving unit into a second language. The first translation section mentioned above is, When translating the source text obtained by the source text acquisition unit into the first language, the unit refers to a specialized term dictionary that records the correspondence between specialized terms and translation information. If a term contained in the source text is a specialized term recorded in the specialized term dictionary, the unit obtains information indicating the pronunciation of the specialized term as translation information corresponding to the term contained in the source text from the specialized term dictionary. In this case, the translation result of the term contained in the source text into the first language is translated to the pronunciation indicated by the obtained information. If information indicating the translation of the specialized term in the first language is obtained as translation information, the unit translates the term contained in the source text into the translation of the specialized term in the first language. The second translation section mentioned above is, The first translation unit translates the technical terms into the second language by using information indicating the pronunciation of the technical terms as translation information obtained from the technical term dictionary, and if the terms contained in the source text obtained by the source text acquisition unit have been translated into the first language, then by using information indicating the pronunciation of the technical terms to convert the pronunciation of the technical terms into phonetic characters corresponding to the second language, or by using the information indicating the pronunciation of the technical terms as is to translate the technical terms into the second language. A translation device characterized by the following features.

2. The first translation section mentioned above is, When the revision reception unit receives a revision of the original text, the revision reception unit translates the revised original text into the first language. The translation device according to claim 1, characterized in that it is a translation device.

3. The second translation section mentioned above is, In addition to translating either the revised original text received by the revision reception unit or the original text obtained by the original text acquisition unit into the second language, the revised original text received by the revision reception unit or the original text obtained by the original text acquisition unit into one or more languages ​​different from the first language and the second language. A translation device according to claim 1 or 2, characterized by the features described above.

4. The first language is English, The first translation section mentioned above is, The original text obtained by the aforementioned original text acquisition unit is translated into English. A translation device according to claim 1 or 2, characterized by the features described above.

5. The translation information corresponding to the aforementioned technical terms is: Information indicating how to pronounce the aforementioned technical term, or information indicating the translation of the aforementioned technical term in the first language, The first translation section mentioned above is, When translating terms contained in the source text obtained by the source text acquisition unit into the first language, the system accepts a selection of either information indicating the pronunciation of the technical terms or information indicating the translation of the technical terms in the first language as translation information. A translation device according to claim 1 or 2, characterized by the features described above.

6. The aforementioned translation section is, If the terms contained in the source text obtained by the source text acquisition unit are translated by the first translation unit using translation information obtained from the specialized terminology dictionary, the term corresponding to that translation information will be used as the return translation result. A translation device according to claim 1 or 2, characterized by the features described above.

7. The system includes a corresponding language identification unit that identifies the corresponding language of the recipient, who is the person to whom the translation by the second translation unit is provided, as the second language. The second translation section mentioned above is, The revised original text received by the revision reception unit is translated into the corresponding language identified by the corresponding language identification unit. A translation device according to claim 1 or 2, characterized by the features described above.

8. The aforementioned corresponding language identification unit is Based on image information showing the image of the person to be provided, the language of the person to be provided is identified. The translation device according to claim 7, characterized in that it is a translation device.

9. The aforementioned corresponding language identification unit is Based on the voice information representing the voice of the person to be served, the language supported by the person to be served is identified. The translation device according to claim 7, characterized in that it is a translation device.

10. The aforementioned corresponding language identification unit is We accept corrections to the identification results of the languages ​​supported by the aforementioned recipients. The translation device according to claim 7, characterized in that it is a translation device.

11. The system includes a first modified text acquisition unit that provides the source text acquired by the source text acquisition unit to a generating AI (Artificial Intelligence), and obtains a modified version of the source text from the generating AI. The first translation section mentioned above is, Instead of the original text obtained by the original text acquisition unit, the revised version of the original text obtained by the first revised version acquisition unit is translated into the first language. A translation device according to claim 1 or 2, characterized by the features described above.

12. The system includes a second modified text acquisition unit that provides the folded translation text from the folded translation unit to a generating AI and obtains a modified version of the folded translation text from the generating AI. The display processing unit, The second correction unit generates the corrected version of the translated text and displays it on the display device. The aforementioned correction acceptance unit is: After the display processing unit displays the corrected version of the line-wrapped translation, the original text acquisition unit accepts the correction of the original text acquired by the original text acquisition unit. A translation device according to claim 1 or 2, characterized by the features described above.

13. The system includes a second modified text acquisition unit that provides the folded translation text from the folded translation unit to a generating AI and obtains a modified version of the folded translation text from the generating AI. The display processing unit, The second correction unit generates the corrected version of the translated text and displays it on the display device. The aforementioned correction acceptance unit is: After the display processing unit displays the revised version of the line-wrapped translation, the system accepts the revision of the original text obtained by the original text acquisition unit, or the revised version of the original text obtained by the first revised text acquisition unit. The translation device according to claim 11, characterized in that it is a translation device.

14. The first revised text acquisition unit further provides the generating AI with attribute information, which is information indicating the level of expertise of the person to whom the translated text by the second translation unit is provided, and acquires a revised version of the original text from the generating AI that corresponds to the level of the person to whom the translated text is provided. The translation device according to claim 11, characterized in that it is a translation device.

15. The source text acquisition unit performs a source text acquisition step to acquire the source text to be translated, The first translation unit performs a first translation step in which it translates the source text obtained in the source text acquisition step into a first language, The reverse translation unit performs a reverse translation step in which it reverses the translation of the text obtained in the first translation step, The display processing unit performs a display processing step that causes the folded translated text obtained by the folded translation step to be displayed on a display device, The correction acceptance unit accepts corrections to the original text after the wrapped translation is displayed in the display processing step, The second translation unit, upon receiving a revision of the original text in the revision acceptance step, executes a second translation step which translates the revised original text received in the revision acceptance step into a second language. The first translation step described above is: When translating the source text obtained in the source text acquisition step into the first language, a specialized term dictionary in which the correspondence between specialized terms and translation information is recorded is referred to, and if a term contained in the source text is a specialized term recorded in the specialized term dictionary, then information indicating the pronunciation of the specialized term is obtained from the specialized term dictionary as translation information corresponding to the term contained in the source text, and the translation result of the term contained in the source text into the first language is translated to the pronunciation indicated by the obtained information, and if information indicating the translation of the specialized term into the first language is obtained as translation information, then the term contained in the source text is translated into the translation of the specialized term into the first language. The second translation step described above is: In the first translation step, if the terms contained in the source text obtained in the source text acquisition step have been translated into the first language using the information indicating the pronunciation of the technical terms as translation information obtained from the technical term dictionary, the technical terms are translated into the second language by converting the pronunciation of the technical terms into phonetic characters corresponding to the second language using the information indicating the pronunciation of the technical terms, or the technical terms are translated into the second language by using the information indicating the pronunciation of the technical terms as is. A translation method characterized by the following:

Images