A method of translating a source language into a target language and a computing device
By generating relational files and using an online writing and translation platform, the source language documents and target language documents are updated synchronously, solving the problem of inefficiency in manual editing after machine translation, improving translation efficiency and quality, and reducing enterprise costs.
Patent Information
- Application Number
- CN202211271047.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-10-17
- Publication Date
- 2025-12-16
- Estimated Expiration
- 2042-10-17
AI Technical Summary
Current machine translation technology requires manual editing and correction, resulting in low translation efficiency, a large talent gap, and delayed and low-quality updates, making it impossible to achieve online synchronization of writing and translation.
By generating a relationship file between the source language document and the target language document, the update points in the target language document are automatically updated. Writing and translation are synchronized using an online writing and translation platform. Sentences are split and translated using computing devices, sentence pairs are stored in a corpus, and the relationship file is used to automatically update the target language document.
It improved translation efficiency, reduced manual editing and correction work, ensured that no updates were missed, improved translation quality, and reduced translation costs for businesses.
Smart Images
Figure CN115630654B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of communication, and in particular to a method for translating a source language into a target language and a computing device. BACKGROUND
[0002] Technical documents provide good support for technology dissemination and product application and maintenance, and are increasingly valued by enterprises in the technology industry. Many enterprises in the technology industry have established their own professional technical document development teams to develop source language documents and translate target language documents. For different markets, source language documents often need to be translated into multiple target language documents.
[0003] Although in recent years the rapid development of artificial intelligence and deep learning has made machine translation more and more widely used. However, machine translation needs to be edited and corrected by human beings after translation. However, relying on human translation, there is a large talent gap, and the translation efficiency is low. Moreover, when the source language document is updated, the updated content (for ease of description, the updated content is referred to as an update point hereinafter) needs to be found by human beings, which is time-consuming and leads to a lag in the translation of the target language document, resulting in low translation efficiency. Moreover, some update points may be missed, so that the translated content corresponding to the update points in the target language document is not updated, resulting in low translation quality of the target language document.
[0004] Therefore, how to improve the translation efficiency, translation quality, reduce the editing and correction work in the translation process, and thus reduce the translation investment cost of enterprises has become a technical problem to be solved. SUMMARY
[0005] To solve the above technical problems, the present application provides a method for translating a source language into a target language and a computing device.
[0006] In a first aspect, the present application provides a method for translating a source language into a target language, the method comprising:
[0007] obtaining at least one first source language module in a source language document, the at least one first source language module being any one or more source language modules in the source language document. It can be understood that a source language module can be a chapter, a paragraph and / or a sentence.
[0008] translating the at least one first source language module into at least one first target language module corresponding thereto, generating an association relationship file between the source language document and the target language document, the target language document comprising the at least one first target language module.
[0009] If any first source language module in the source language document is updated, the corresponding first target language module is updated according to the association relationship file, compared with manually searching for the update point, the translation efficiency is improved, and the update point is not missed, and the translation quality is improved.
[0010] In a possible implementation, the translation of the at least one first source language module into the at least one first target language module corresponding thereto, and the generation of the association relationship file between the source language document and the target language document, comprise:
[0011] Each first source language module in the at least one first source language module is respectively subjected to sentence splitting, and at least one source language sentence is respectively obtained;
[0012] Each source language sentence in the at least one source language sentence is translated into a corresponding target language sentence;
[0013] Each source language sentence and the corresponding target language sentence are associated in pairs to generate each sentence pair; wherein each sentence pair is stored in the corpus as corpus; and / or
[0014] The ID of the source language document, the ID of the target language document, the document ID mapping relationship between the source language document and the target language document, the first position ID of each source language sentence in the source language document, the second position ID of each target language sentence in the target language document, and the position ID mapping relationship between the first position ID and the second position ID are determined;
[0015] The association relationship file is determined according to each sentence pair, the document ID mapping relationship, and the position ID mapping relationship.
[0016] In a possible implementation, the association relationship file comprises: each sentence pair, the document ID mapping relationship, and / or the position ID mapping relationship.
[0017] In a possible implementation, the association relationship file comprises: the language attribute of the source language document, the language attribute of the target language document, the mutual translation relationship between the source language document and the target language document, the position relationship between each first source language module, the position relationship between each source language sentence, the position relationship between each first target language module, and the position relationship between each target language sentence.
[0018] In a possible implementation, if any first source language module in the source language document is updated, the corresponding first target language module is updated according to the association relationship file, comprising:
[0019] If any one of the source language sentences in the first source language module is updated, the ID of the source language document where the first source language module is located and the first position ID of any one of the source language sentences are obtained;
[0020] According to the ID of the source language document where the first source language module is located and the mapping relationship between the document IDs in the association relationship file, the ID of the target language document that needs to be updated is determined;
[0021] According to the first position ID of any one of the source language sentences and the mapping relationship between the position IDs in the association relationship file, the second position ID of the target language sentence corresponding to the source language sentence in the target language document that needs to be updated is determined;
[0022] The target language sentence with the second position ID is synchronously updated, which improves the translation efficiency compared with manually searching for the update point, and does not miss the update point, thereby improving the translation quality.
[0023] In a second aspect, the present application provides a computing device, which comprises:
[0024] The online writing unit is configured to obtain at least one first source language module in a source language document, the at least one first source language module being any one or more source language modules in the source language document;
[0025] The online submission unit is connected to the online writing unit; the online submission unit is configured to obtain the at least one first source language module and submit it to the online translation unit;
[0026] The online translation unit is connected to the online submission unit; the online translation unit is configured to translate the at least one first source language module into at least one first target language module corresponding thereto; and further configured to generate an association relationship file between the source language document and a target language document, the target language document comprising the at least one first target language module; and further configured to, in the case that any one of the first source language modules in the source language document is updated, update the first target language module corresponding thereto according to the association relationship file;
[0027] The file management unit is connected to the online writing unit and the online translation unit respectively; the file management unit is configured to store the association relationship file, the source language document and / or the target language document.
[0028] In a possible implementation, the online writing unit is specifically configured to determine the ID of the source language document and the first position ID of each source language sentence in the source language document;
[0029] The online submission unit is specifically configured to obtain the ID of the source language document and the first position ID of each source language sentence in the source language document, and submit it to the online translation unit;
[0030] The online translation unit is specifically configured to respectively perform sentence splitting on each of the at least one first source language module to obtain at least one source language sentence respectively; translate each of the at least one source language sentence into a corresponding target language sentence; associate each source language sentence with the corresponding target language sentence to generate a sentence pair; determine an ID of the target language document and a second position ID of each target language sentence in the target language document; determine a document ID mapping relationship between the source language document and the target language document, and a position ID mapping relationship between each first position ID and each second position ID; and determine the association relationship file according to each sentence pair, the document ID mapping relationship, and / or the position ID mapping relationship.
[0031] The online translation unit comprises a corpus unit; and the corpus unit is configured to store each sentence pair.
[0032] In a possible implementation, the association relationship file comprises each sentence pair, the document ID mapping relationship, and / or the position ID mapping relationship.
[0033] In a possible implementation, the association relationship file comprises a language attribute of the source language document, a language attribute of the target language document, a mutual translation relationship between the source language document and the target language document, a position relationship between each first source language module, a position relationship between each source language sentence, a position relationship between each first target language module, and a position relationship between each target language sentence.
[0034] In a possible implementation, the online writing unit is specifically configured to, if any one of the source language sentences in the first source language module is updated, obtain an ID of a source language document in which the first source language module is located and a first position ID of the source language sentence.
[0035] The online submission unit is specifically configured to submit the ID of the source language document in which the first source language module is located and the first position ID of the source language sentence to the online translation unit.
[0036] The online translation unit is specifically configured to obtain the association relationship file from the file management unit, determine an ID of a target language document that needs to be updated according to the ID of the source language document in which the first source language module is located and the document ID mapping relationship in the association relationship file, determine a second position ID of a target language sentence corresponding to the source language sentence in the target language document that needs to be updated according to the first position ID of the source language sentence and the position ID mapping relationship in the association relationship file, and synchronously update the target language sentence with the second position ID.
[0037] It should be noted that the beneficial effects of the computing device in the second aspect and various possible implementations thereof can refer to the beneficial effects of the corresponding method in the first aspect, which will not be described here.
[0038] In a third aspect, the present application provides an apparatus for translating a source language into a target language, comprising at least one processor configured to perform a program stored in a memory, when the program is executed, causing the apparatus to perform the following steps:
[0039] As the method in the first aspect and various possible implementations thereof.
[0040] In one possible implementation, the apparatus further comprises the memory described above. Optionally, the processor and the memory can be integrated together.
[0041] In another possible implementation, the memory described above is arranged outside the apparatus.
[0042] In a fourth aspect, the present application provides a computer program product comprising instructions which, when the computer program product is executed on a computer, cause the method as in the first aspect and various possible implementations thereof to be performed by the computer.
[0043] In a fifth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program, which, when executed by a processor, causes the method as in the first aspect and various possible implementations thereof to be performed. BRIEF DESCRIPTION OF DRAWINGS
[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed by the embodiments. Obviously, the drawings described in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.
[0045] Figure 1 A schematic diagram of a computing device provided by an embodiment of the present application;
[0046] Figure 2 A flowchart of a method for translating a source language into a target language provided by an embodiment of the present application;
[0047] Figure 3 A structural diagram of an apparatus for translating a source language into a target language provided by an embodiment of the present application. DETAILED DESCRIPTION
[0048] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the following will describe the specific embodiments of the present application in detail with reference to the drawings.
[0049] It should be noted that the term "and / or" in the present application is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. The terms "first" and "second" in the specification and claims of the embodiments of the present application are used to distinguish different objects, and are not used to describe the specific order of the target objects. For example, the first position ID and the second position ID are used to distinguish different position IDs, and are not used to describe the specific order of the target objects. In the embodiments of the present application, the words "exemplary", "for example" or "for instance" are used to represent examples, illustrations or descriptions. Any embodiment or design scheme described as "exemplary", "for example" or "for instance" in the embodiments of the present application should not be interpreted as more advantageous than other embodiments or design schemes. Rather, the words "exemplary" or "for example" are intended to present the relevant concepts in a specific manner. In the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise specified.
[0050] In one example, the writing of the source language document can use offline writing editing tools such as office, Arbortext, etc., or use online writing editing tools such as markdown and online writing editing tools developed by each enterprise for multi-person synchronous development. The translation of the target language document can also use offline writing editing tools or online writing editing tools for manual translation. However, the writing of the source language document and the translation of the target language document are carried out separately, and cannot be carried out synchronously online, and the translation efficiency is low.
[0051] In another example, the writing of the source language document also uses offline writing editing tools such as office, Arbortext, etc., or uses online writing editing tools such as markdown and online writing editing tools developed by each enterprise for multi-person synchronous development. The translation of the target language document can use computer assistance translation (CAT) tools such as Trados, etc. After the writing of the source language document is completed, it is published in the required format and then submitted offline to the CAT tool. The CAT tool translates the source language document into the target language document. In this translation mode, the writing of the source language document and the translation of the target language document are completed on two platforms respectively, and cannot be carried out synchronously online, and the translation efficiency is low.
[0052] To solve the above technical problems, the embodiment of the present application provides a method for translating a source language into a target language, which is based on a computing device 100 provided by the embodiment of the present application. The computing device 100 can be used as an online writing & translation platform. A schematic diagram of the computing device 100 is shown in Figure 1 The computing device 100 comprises an online writing unit 101, an online submission unit 102, an online translation unit 103 and a file management unit 104. It can be understood that the online translation unit 103 can further comprise a corpus unit 105. The online writing unit 101 can be a writing editing tool such as office, Arbortext, etc. The online translation unit 103 can be a CAT tool such as Trados, etc. The computing device 100 realizes the connection between the writing editing tool and the translation tool.
[0053] The online writing unit 101 is used to obtain at least one first source language module in a source language document, wherein the at least one first source language module is any one or more source language modules in the source language document. It can be understood that the source language module can be a chapter, a paragraph and / or a sentence.
[0054] The online submission unit 102 is connected with the online writing unit 101. The online submission unit 101 is used to obtain the at least one first source language module from the online writing unit 101 and submit it to the online translation unit 103.
[0055] The online translation unit 103 is connected with the online submission unit 102. The online translation unit 103 is used to translate the at least one first source language module into at least one first target language module corresponding to the at least one first source language module; is further used to generate a correlation file between the source language document and a target language document, wherein the target language document comprises the at least one first target language module; and is further used to update the first target language module corresponding to any one first source language module in the source language document according to the correlation file when the any one first source language module in the source language document is updated.
[0056] The file management unit 104 is connected with the online writing unit 101 and the online translation unit 103 respectively. The file management unit 104 is used to store the correlation file, the source language document and / or the target language document.
[0057] In a possible implementation, the online writing unit 101 is specifically used to determine an ID of the source language document and each first position ID of each source language sentence in the source language document;
[0058] The online submission unit 102 is specifically used to obtain the ID of the source language document and the each first position ID of the each source language sentence in the source language document and submit them to the online translation unit 103.
[0059] The online translation unit 103 is specifically configured to respectively perform sentence splitting on each of the at least one first source language module to obtain at least one source language sentence respectively; translate each of the at least one source language sentence into a corresponding target language sentence; associate each of the source language sentence with the corresponding target language sentence to generate a sentence pair; determine an ID of the target language document and a second position ID of each of the target language sentences in the target language document; determine a document ID mapping relationship between the source language document and the target language document, and a position ID mapping relationship between the first position ID and the second position ID; and determine the association relationship file according to the sentence pair, the document ID mapping relationship and / or the position ID mapping relationship.
[0060] The corpus unit 105 is configured to store the sentence pair.
[0061] It can be understood that the association relationship file includes the sentence pair, the document ID mapping relationship and the position ID mapping relationship.
[0062] In a possible implementation, the association relationship file includes a language attribute of the source language document, a language attribute of the target language document, a mutual translation relationship between the source language document and the target language document, a position relationship between the first source language modules, a position relationship between the source language sentences, a position relationship between the first target language modules, and a position relationship between the target language sentences.
[0063] In a possible implementation, the online writing unit 101 is specifically configured to, if any of the source language sentences in the first source language module is updated, obtain an ID of the source language document in which the first source language module is located and a first position ID of the source language sentence.
[0064] The online submission unit 102 is specifically configured to submit the ID of the source language document in which the first source language module is located and the first position ID of the source language sentence to the online translation unit 103.
[0065] The online translation unit 103 is specifically configured to obtain the association relationship file from the file management unit 104, and determine an ID of the target language document that needs to be updated according to the ID of the source language document in which the first source language module is located and the document ID mapping relationship in the association relationship file; determine a second position ID of the target language sentence corresponding to the source language sentence in the target language document that needs to be updated according to the first position ID of the source language sentence and the position ID mapping relationship in the association relationship file; and synchronously update the target language sentence with the second position ID.
[0066] Next, a method for translating a source language into a target language proposed in the embodiments of the present application is described in detail. The method is implemented based on the computing device 100 as shown in Figure 1 The flowchart of the method is shown in Figure 2
[0067] In a possible implementation, the method for translating a source language into a target language provided in the embodiments of the present application is implemented by the following steps:
[0068] S201, the online writing unit 101 acquires at least one first source language module in the source language document.
[0069] First of all, it should be noted that in the embodiments of the present application, the computing device 100 can be used as an online writing & translation platform, including an online writing unit 10, such as a writing editing tool, such as office, Arbortext, etc., an online submission unit 102, an online translation unit 103, such as a CAT tool, and a file management unit 104. It can be understood that the online translation unit 103 can include a corpus unit 105. It can be understood that the corpus unit 105 includes a shared corpus and a private corpus.
[0070] The user can write a source language document in a writing editing tool, such as office, Arbortext, etc. Or the user can also develop a source language document in a writing editing tool, such as markdown and various writing editing tools developed by enterprises. After writing, the source language document is saved to the file management unit 104. If the user selects to translate at least one first source language module in the source language document, the online writing unit 101 in the computing device 100 acquires the at least one first source language module. It can be understood that the at least one first source language module is any one or more source language modules in the source language document. The source language module can be a chapter, a paragraph and / or a sentence.
[0071] S202, the online submission unit 102 acquires the at least one first source language module and submits it online to the online translation unit 103.
[0072] In the embodiments of the present application, the online submission unit 102 can acquire the at least one first source language module from the online writing unit 101 and submit it online to the online translation unit 103, which improves the translation efficiency compared to the offline submission of the source language document required by manual translation.
[0073] S203, the online translation unit 103 translates the at least one first source language module into at least one first target language module corresponding thereto, and generates an association relationship file between the source language document and the target language document.
[0074] In the embodiment of the present application, the online translation unit 103 translates the at least one first source language module into at least one first target language module corresponding thereto, to generate a correlation file between the source language document and the target language document. The target language document includes the at least one first target language module. It can be understood that the target language document can be stored in the file management unit 104.
[0075] In one example, the online translation unit 103 respectively performs sentence splitting on each of the at least one first source language module to respectively obtain at least one source language sentence. The online translation unit 103 translates each of the at least one source language sentence into a target language sentence corresponding thereto. The online translation unit 103 performs sentence pair correlation on each of the source language sentence and the target language sentence corresponding thereto to generate a sentence pair. Each of the sentence pairs is stored in the corpus unit 105 as a corpus.
[0076] It should be noted that in S201, the online writing unit 101 can also determine the ID of the source language document and the first position ID of each of the source language sentences in the source language document. In S202, the online submission unit 102 can also obtain the ID of the source language document and the first position ID of each of the source language sentences in the source language document from the online writing unit 101, and submit them online to the online translation unit 103.
[0077] In one example, the online translation unit 103 determines the ID of the target language document, the second position ID of each of the target language sentences in the target language document, and the position ID mapping relationship between the first position ID and the second position ID, the document ID mapping relationship between the source language document and the target language document.
[0078] In a possible implementation, the position ID mapping relationship is obtained by the following way:
[0079] In the translation process, after translating a sentence pair of a source language sentence and a target language sentence, the online writing unit 101 determines the first position ID of the source language sentence in the source language document and submits it online to the online translation unit 103 through the online submission unit 102. The online translation unit 103 maps and correlates the first position ID with the second position ID of the target language sentence corresponding to the source language sentence in the target language document. The mapping and correlation of each of the first position ID of each of the source language sentences in the source language document and each of the second position ID of each of the target language sentences in the target language document, i.e., the ID mapping relationship.
[0080] In the embodiment of the present application, the online translation unit 103 determines the association relationship file according to the respective sentence pairs, the position ID mapping relationship, and / or the source language document ID and / or the target language document ID mapping relationship. Specifically, the online translation unit 103 records the respective sentence pairs, the position ID mapping relationship, and / or the document ID mapping relationship, and the respective sentence pairs, the position ID mapping relationship, and / or the document ID mapping relationship are taken as a part of the association relationship file. It should be noted that if the online translation unit 103 is a CAT tool such as Trados, the sentence pairs in the association relationship file exist in the XML localisation interchange file format (XLIFF). It should also be noted that the association relationship file further includes the language attribute of the source language document, the language attribute of the target language document, the mutual translation relationship between the source language document and the target language document, the position relationship between the respective first source language modules, the position relationship between the respective source language sentences, the position relationship between the respective first target language modules, and the position relationship between the respective target language sentences.
[0081] For example, the language attribute can be Chinese, English, Japanese, etc. The embodiment of the present application does not make a specific limitation on the language attribute, which is only an example. The mutual translation relationship between the source language document and the target language document can be Chinese-English translation, Chinese-Japanese translation, and English-Japanese translation. The embodiment of the present application does not make a specific limitation on the mutual translation relationship, which is only an example. The position relationship between the respective first source language modules can be the front-back position relationship between the respective first source language modules, for example, the first source language module A is located before the first source language module B. The position relationship between the respective source language sentences and the position relationship between the respective first target language modules are similar to the position relationship between the respective first source language modules, which will not be described herein.
[0082] S204, if any first source language module in the source language document is updated, the online translation unit 103 updates the corresponding first target language module according to the association relationship file.
[0083] In the embodiment of the present application, if any first source language module in the source language document is updated, the online translation unit 103 updates the corresponding first target language module according to the association relationship file.
[0084] In one example, if any one source language sentence in the first source language module is updated, the online writing unit 101 obtains the ID of the source language document in which the first source language module is located and the first position ID of the any one source language sentence; the online submitting unit 102 submits the ID of the source language document in which the first source language module is located and the first position ID of the any one source language sentence to the online translation unit 103; the online translation unit 103 obtains the association relationship file from the file management unit 104, and determines the ID of the target language document that needs to be updated according to the ID of the source language document in which the first source language module is located and the document ID mapping relationship in the association relationship file; determines the second position ID of the target language sentence corresponding to the source language sentence in the target language document that needs to be updated according to the first position ID of the any one source language sentence and the position ID mapping relationship in the association relationship file; and synchronously updates the target language sentence with the second position ID.
[0085] For example, if the source language document needs to be updated, the online writing unit 101 obtains the source language document from the file management unit 104, and saves it to the file management unit 104 after the user completes the update. The online writing unit 101 compares the source language document and the updated source language document, and obtains the ID of the source language document and the first position ID of the update point. The online submitting unit 102 obtains the ID of the source language document and the first position ID of the update point from the online writing unit 101, and submits them to the online translation unit 103. The online translation unit 103 obtains the association relationship file from the file management unit 104, and determines the ID of the target language document that needs to be updated according to the document ID mapping relationship in the association relationship file and the ID of the source language document, and obtains the target language document that needs to be updated from the file management unit 104 according to the ID of the target language document; determines the second position ID of the target language sentence corresponding to the update point in the target language document that needs to be updated according to the position ID mapping relationship in the association relationship file and the first position ID of the update point. The online translation unit 103 synchronously updates the target language sentence with the second position ID, which improves the translation efficiency compared to manually finding the update point, and does not miss the update point, thereby improving the translation quality.
[0086] It should be noted that the online translation unit 103 can match any source language sentence in the source language document to be translated with the source language sentence in any sentence pair in the shared corpus or the private corpus. The private corpus can be shared with other users to improve the translation efficiency. If any source language sentence in the source language document to be translated is the same as the source language sentence in any sentence pair in the corpus unit 105, the online translation unit 103 directly presents the target language sentence in the sentence pair to the user. The user can directly select the target language sentence in the sentence pair as the target language sentence of any source language sentence in the source language document to be translated. If any source language sentence in the source language document to be translated has a high similarity, for example, 90%, with the source language sentence in any sentence pair in the corpus unit 105, the online translation unit 103 directly presents the target language sentence in the sentence pair to the user. The user can edit the target language sentence in the sentence pair, and the edited target language sentence is used as the target language sentence of any source language sentence in the source language document to be translated. In this way, for the repeated source language sentences, the corresponding target language sentences can be directly found in the corpus unit 105, without the need to translate again, thereby improving the translation efficiency and reducing the editing and correction work in the translation process.
[0087] As can be seen from the above, the computing device 100 provided by the embodiments of the present application realizes online synchronization of writing and translation. Since the writing editing tool is connected with the translation tool, any one or more source language modules written by the user in the writing editing tool can be submitted to the online translation unit 103 for online synchronous translation through the online submission unit 102. Compared with offline submission of the source language document for manual translation, the translation efficiency is improved. When the source language document is updated, the update point can be found through the association relationship file, and the target language document is updated online, which improves the translation efficiency compared with manual searching for the update point, and the update point is not missed, thereby improving the translation quality. In addition, if the online translation unit 103 is a CAT tool, such as Trados, it has its own corpus. A large number of sentence pairs are stored in the corpus. Therefore, when the source language sentence of the source language document to be translated is the same as the source language sentence of the sentence pair stored in the corpus, the target language sentence of the sentence pair stored in the corpus can be directly used as the translation content of the source language sentence, thereby reducing the editing and correction work in the translation process. In summary, the embodiments of the present application reduce the enterprise translation investment cost.
[0088] Referring to Figure 3The embodiment of the present application further provides a device 300 for translating a source language into a target language, which is used to implement the operations performed by the method embodiments. The device 300 for translating a source language into a target language can be a chip system. In the embodiment of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.
[0089] The device 300 for translating a source language into a target language includes at least one processor 310, which is used to implement the functions of the online translation unit 103 provided by the embodiment of the present application. The device 300 for translating a source language into a target language can further include a communication interface 320. In the embodiment of the present application, the communication interface 320 can be a transceiver, a circuit, a bus, a module or other types of communication interfaces, which are used to communicate with other devices through a transmission medium.
[0090] When the device 300 for translating a source language into a target language is used to perform the operations performed by the method embodiments, the communication interface 320 is used to acquire at least one first source language module in a source language document; and the processor 310 is used to translate the at least one first source language module into at least one first target language module corresponding thereto, to generate an association relationship file between the source language document and a target language document; and if any first source language module in the source language document is updated, the corresponding first target language module is updated according to the association relationship file.
[0091] The processor 310 can also be used to perform other corresponding steps or operations in addition to the steps or operations in the method embodiments, which will not be described here.
[0092] The device 300 for translating a source language into a target language can further include at least one memory 330, which is used to store program instructions and / or data. The memory 330 is coupled with the processor 310. The coupling in the embodiment of the present application is an indirect coupling or communication connection between devices, units or modules, which can be electrical, mechanical or other forms, and is used for information interaction between devices, units or modules. The processor 310 can operate in cooperation with the memory 330. The processor 310 can execute the program instructions stored in the memory 330. In a possible implementation, at least one of the at least one memory can be integrated with the processor. In another possible implementation, the memory 330 is located outside the device 300 for translating a source language into a target language.
[0093] The specific connection medium between the communication interface 320, the processor 310 and the memory 330 is not limited in the embodiment of the present application. In the embodiment of the present application, the memory 330, the processor 310 and the communication interface 320 are connected through a bus 340. Figure 3 Figure 3 The connection mode between other components is indicated by a thick line, which is only illustrative and not limited. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 3 Only one thick line is used, but it does not mean that there is only one bus or one type of bus.
[0094] The embodiment of the present application provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is executed by a processor, and each step of the method for translating a source language into a target language as shown in the figure is executed. Figure 2
[0095] Based on the same concept as the above method embodiment, the embodiment of the present application also provides a computer program product including instructions, when the computer program product runs on a computer, so that the computer executes each step of the method for translating a source language into a target language as shown in the figure. Figure 2
[0096] It should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for translating a source language into a target language, characterized in that, The method includes: Obtain at least one first source language module from the source language document, wherein the at least one first source language module is any one or more source language modules in the source language document; Each of the at least one first source language modules is split into sentences to obtain at least one source language sentence; Translate each source language sentence in the at least one source language sentence into its corresponding target language sentence; Each source language sentence and its corresponding target language sentence are paired and associated to generate sentence pairs; wherein, each sentence pair is stored as corpus in a corpus; and / or Determine the ID of the source language document, the ID of the target language document, the document ID mapping relationship between the source language document and the target language document, the first position ID of each source language sentence in the source language document, the second position ID of each target language sentence in the target language document, and the position ID mapping relationship between the first position ID and the second position ID; Based on the sentence pairs, the document ID mapping relationship, and the location ID mapping relationship, the associated files are determined; The target language document includes at least one first target language module; If any of the first source language modules in the source language document is updated, then the corresponding first target language module is updated according to the association file.
2. The method according to claim 1, characterized in that, The association file includes: the sentence pairs, the document ID mapping relationship, and / or the location ID mapping relationship.
3. The method according to claim 1 or 2, characterized in that, The association file includes: the language attributes of the source language document, the language attributes of the target language document, the mutual translation relationship between the source language document and the target language document, the positional relationship between each first source language module, the positional relationship between each source language sentence, the positional relationship between each first target language module, and the positional relationship between each target language sentence.
4. The method according to claim 2, characterized in that, If any first source language module in the source language document is updated, then updating the corresponding first target language module according to the association file includes: If any source language sentence in the first source language module is updated, then obtain the ID of the source language document where the first source language module is located and the first position ID of the source language sentence. Based on the ID of the source language document containing the first source language module and the document ID mapping relationship in the association file, determine the ID of the target language document that needs to be updated; Based on the mapping relationship between the first position ID of any source language sentence and the position ID in the association file, determine the second position ID of the target language sentence in the target language document that needs to be updated, which corresponds to the source language sentence. The target language sentence of the second position ID is updated synchronously.
5. A computing device, characterized in that, include: An online writing unit is used to obtain at least one first source language module from a source language document, wherein the at least one first source language module is any one or more source language modules in the source language document; The online submission unit is connected to the online writing unit; The online submission unit is used to obtain the at least one first source language module and submit it online to the online translation unit; An online translation unit is connected to the online submission unit; the online translation unit is used to split each of the at least one first source language modules into sentences to obtain at least one source language sentence. The process involves translating each source language sentence in the at least one source language sentence into its corresponding target language sentence; associating each source language sentence with its corresponding target language sentence to generate sentence pairs; wherein each sentence pair is stored as corpus in a corpus; and / or determining the ID of the source language document, the ID of the target language document, the document ID mapping relationship between the source language document and the target language document, each first position ID of each source language sentence in the source language document, each second position ID of each target language sentence in the target language document, and the position ID mapping relationship between the first position ID and the second position ID; determining an association file based on the sentence pairs, the document ID mapping relationship, and the position ID mapping relationship; the target language document includes the at least one first target language module; and further, when any first source language module in the source language document is updated, updating the corresponding first target language module according to the association file. The file management unit is connected to both the online writing unit and the online translation unit; the file management unit is used to store the associated files, source language documents, and / or target language documents.
6. The computing device according to claim 5, characterized in that, The online writing unit is specifically used to determine the ID of the source language document and the ID of each first position of each source language sentence in the source language document; The online submission unit is specifically used to obtain the ID of the source language document and the IDs of the first positions of each source language sentence in the source language document, and submit them online to the online translation unit; The online translation unit includes a corpus unit; the corpus unit is used to store sentence pairs.
7. The computing device according to claim 6, characterized in that, The association file includes: the sentence pairs, the document ID mapping relationship, and / or the location ID mapping relationship.
8. The computing device according to claim 6 or 7, characterized in that, The association file includes: the language attributes of the source language document, the language attributes of the target language document, the mutual translation relationship between the source language document and the target language document, the positional relationship between each first source language module, the positional relationship between each source language sentence, the positional relationship between each first target language module, and the positional relationship between each target language sentence.
9. The computing device according to claim 7, characterized in that, The online writing unit is specifically used to obtain the ID of the source language document where the first source language module is located and the first position ID of the source language sentence if any source language sentence in the first source language module is updated. The online submission unit is specifically used to submit the ID of the source language document containing the first source language module and the first position ID of any source language sentence to the online translation unit online. The online translation unit is specifically used to obtain the association file from the file management unit, and determine the ID of the target language document that needs to be updated based on the ID of the source language document where the first source language module is located and the document ID mapping relationship in the association file; determine the second position ID of the target language sentence corresponding to the source language sentence in the target language document that needs to be updated based on the first position ID of any source language sentence and the position ID mapping relationship in the association file; and synchronously update the target language sentence with the second position ID.
Citation Information
Patent Citations
Computer assisted natural language translation
CN101826072A
Corpus building and filtering method and system
CN114780667A