Information processing device and information processing program

Abstract

To provide an information processor and an information processing program which can perform summarization processing even when a processing target is a document of a language which is not a target of summarization processing.SOLUTION: An information processor 10 has a CPU 11. The CPU 11 determines whether the language of document data is a first language, which is not a target of summarization processing, translates the document data into a second language as a target of the summarization processing when the language is determined to be the first language, performs summarization processing on the document data translated in the second language, and re-translates the document data in the second language obtained by the summarization processing, into the first language.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and an information processing program.

Background Art

[0002] For example, Patent Document 1 describes a document summarization apparatus that creates a summary document from an input document. This document summarization apparatus includes an input means for inputting a first language document and at least one or more other language documents translated into the first language, a common part extraction means for extracting a common part from the first language document and the other language documents input by the input means, and a summary document creation means for creating a summary document based on the common information extracted by the common part extraction means.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, various summarization services such as IBM (registered trademark)'s summarization service (Watson Natural Language Understanding) and Python's Sumy are provided.

[0005] In these summarization services, since the corresponding languages are limited to some languages such as English and Japanese, summarization processing cannot be performed for languages that are not supported.

[0006] An object of the present disclosure is to provide an information processing apparatus and an information processing program capable of performing summarization processing even on a document in a language for which summarization processing is not supported.

Means for Solving the Problems

[0007] To achieve the above objective, the information processing device according to the first embodiment includes a processor, which determines whether the language described in the document data is a first language that does not support summarization processing, and if it is determined to be the first language, translates the document data into a second language that supports summarization processing, performs the summarization processing on the translated document data obtained by translating into the second language, and re-translates the summarized document data in the second language obtained by performing the summarization processing back into the first language.

[0008] Furthermore, in the information processing device according to the second embodiment, the first language and the second language are pre-associated with each other in the information processing device according to the first embodiment.

[0009] Furthermore, in the information processing device according to the third embodiment, the second language is a language determined based on its affinity with the first language, as in the information processing device according to the second embodiment.

[0010] Furthermore, the information processing device according to the fourth embodiment performs control in the information processing device according to the first embodiment by displaying a setting screen that allows the processor to set either an automatic mode in which the second language is automatically specified, or a manual mode in which the second language is specified by the user.

[0011] Furthermore, the information processing device according to the fifth embodiment allows the user to configure whether or not the setting screen displays the summarized document data obtained by retranslating the first language together with the document data in the first language, and whether or not to display a confirmation and correction screen for confirming and correcting the summarized document data.

[0012] Furthermore, in order to achieve the above objective, the information processing program according to the sixth embodiment determines whether the language described in the document data is a first language that does not support summarization processing, and if it is determined to be the first language, it causes the computer to translate the document data into a second language that supports summarization processing, perform the summarization processing on the translated document data obtained by translating into the second language, and then re-translate the summarized document data in the second language obtained by performing the summarization processing back into the first language. [Effects of the Invention]

[0013] According to the first and sixth embodiments, the summarization process can be performed even on documents in languages ​​that do not support summarization.

[0014] According to the second embodiment, the effect is that documents in languages ​​that do not support summarization processing can be translated into languages ​​that do support summarization processing.

[0015] According to the third embodiment, the effect is that documents in a language that does not support summarization processing can be translated into a language that has high affinity with that language and supports summarization processing.

[0016] According to the fourth aspect, the effect is that either automatic mode or manual mode can be selectively set when specifying the target language for translation.

[0017] According to the fifth aspect, it has the effect of allowing users to review and correct documents by comparing the document before summarization with the document after summarization. [Brief explanation of the drawing]

[0018] [Figure 1] This is a block diagram showing an example of the electrical configuration of an information processing device according to an embodiment. [Figure 2] This is a block diagram showing an example of the functional configuration of an information processing apparatus according to the embodiment. [Figure 3]It is a diagram showing an example of a non-corresponding language table according to an embodiment. [Figure 4] It is a diagram showing an example of a corresponding language table according to an embodiment. [Figure 5] It is a diagram showing an example of document data according to an embodiment. [Figure 6] It is a diagram showing an example of translated document data according to an embodiment. [Figure 7] It is a diagram showing an example of a summary processing setting screen according to an embodiment. [Figure 8] It is a front view showing an example of a confirmation and correction screen according to an embodiment. [Figure 9] It is a flowchart showing an example of the flow of processing by an information processing program according to an embodiment.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of a mode for implementing the technology of the present disclosure will be described in detail with reference to the drawings. Note that components and processes that perform the same functions may be given the same reference numerals throughout the drawings, and redundant explanations may be omitted as appropriate. Each drawing is only schematically shown to the extent that the technology of the present disclosure can be sufficiently understood. Therefore, the technology of the present disclosure is not limited only to the illustrated examples. In addition, in the present embodiment, descriptions of configurations that are not directly related to the technology of the present disclosure and well-known configurations may be omitted.

[0020] FIG. 1 is a block diagram showing an example of the electrical configuration of an information processing apparatus 10 according to the present embodiment. (31]]

[0021] As shown in FIG. 1, the information processing apparatus 10 according to the present embodiment includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, an input / output interface (I / O) 14, a storage unit 15, a display unit 16, an operation unit 17, and a communication unit 18.

[0022] As an example, the information processing device 10 in this embodiment may be a general-purpose computer device such as a server computer or a personal computer (PC).

[0023] The CPU 11, ROM 12, RAM 13, and I / O 14 are connected to each other via a bus. The I / O 14 is connected to various functional units, including a storage unit 15, a display unit 16, an operation unit 17, and a communication unit 18. These functional units are capable of communicating with the CPU 11 via the I / O 14.

[0024] The control unit is comprised of a CPU 11, ROM 12, RAM 13, and I / O 14. The control unit may be configured as a sub-control unit that controls the operation of a part of the information processing device 10, or as part of a main control unit that controls the operation of the entire information processing device 10. Integrated circuits or IC chipsets, such as LSIs (Large Scale Integrations), are used in part or all of each block of the control unit. Individual circuits may be used for each of the above blocks, or circuits that integrate part or all of them may be used. The above blocks may be provided as a single unit, or some of the blocks may be provided separately. Furthermore, parts of each of the above blocks may be provided separately. For the integration of the control unit, dedicated circuits or general-purpose processors may be used, not limited to LSIs.

[0025] For example, the storage unit 15 may be an HDD (Hard Disk Drive), an SSD (Solid State Drive), or flash memory. The storage unit 15 stores an information processing program 15A for executing the document summarization process according to this embodiment. This information processing program 15A may also be stored in the ROM 12.

[0026] The information processing program 15A may, for example, be pre-installed on the information processing device 10. The information processing program 15A may also be implemented by storing it on a non-volatile storage medium or distributing it via a network and installing it on the information processing device 10 as appropriate. Examples of non-volatile storage mediums include CD-ROMs (Compact Disc Read Only Memory), magneto-optical disks, HDDs, DVD-ROMs (Digital Versatile Disc Read Only Memory), flash memory, and memory cards.

[0027] The display unit 16 may include, for example, a liquid crystal display (LCD), an organic EL (electroluminescence) display, or the like. The display unit 16 may also have an integrated touch panel. The operation unit 17 is equipped with, for example, a keyboard, mouse, or other device for operation input. The display unit 16 and the operation unit 17 receive various instructions from the user of the information processing device 10. The display unit 16 displays various information such as the results of processing performed in response to instructions received from the user, and notifications regarding processing.

[0028] The communication unit 18 is connected to a network such as the Internet, LAN (Local Area Network), or WAN (Wide Area Network), and is capable of communicating with other external devices such as other information processing devices and image forming devices via the network.

[0029] By the way, as mentioned above, existing summarization services such as IBM's (registered trademark) Watson Natural Language Understanding and Python's Sumy are limited to certain languages ​​such as English and Japanese, and therefore cannot perform summarization processing for languages ​​that are not supported.

[0030] The information processing device 10 according to this embodiment determines whether the language described in the document data is a first language that does not support summarization processing. If it determines that it is a first language, it translates the document data into a second language that supports summarization processing. It then performs summarization processing on the translated document data obtained by translating into the second language, and finally re-translates the summarized document data in the second language obtained by summarization processing back into the first language.

[0031] Specifically, the CPU 11 of the information processing device 10 according to this embodiment functions as the various parts shown in Figure 2 by writing the information processing program 15A stored in the storage unit 15 to the RAM 13 and executing it. Note that the CPU 11 is an example of a processor.

[0032] Figure 2 is a block diagram showing an example of the functional configuration of the information processing device 10 according to this embodiment.

[0033] As shown in Figure 2, the CPU 11 of the information processing device 10 according to this embodiment functions as a processing setting unit 11A, an acquisition unit 11B, a language determination unit 11C, a translation processing unit 11D, a summarization processing unit 11E, a retranslation processing unit 11F, and an output unit 11G.

[0034] The storage unit 15 according to this embodiment stores a non-supported language table 151 and a supported language table 152.

[0035] Figure 3 shows an example of the unsupported language table 151 according to this embodiment.

[0036] As shown in Figure 3, the unsupported language table 151 contains pre-associated language codes and target languages ​​for unsupported languages, which are languages ​​that are not supported by the summarization process. The target languages ​​for automatic translation are those supported by the summarization process that have a relatively high affinity with the unsupported language. For example, since "Korean" is unsupported, it is associated with "Japanese," which has a high affinity. The unsupported language is just one example of a first language. Note that unsupported languages ​​differ depending on the type of summarization service, so it is desirable to create an unsupported language table 151 for each type of summarization service.

[0037] Figure 4 shows an example of the corresponding language table 152 according to this embodiment.

[0038] As shown in Figure 4, the corresponding language table 152 has language codes pre-associated and registered for the corresponding languages ​​that support summarization processing. The corresponding language is an example of a second language. Note that the corresponding languages ​​differ for each type of summarization service, so it is desirable to create a corresponding language table 152 for each type of summarization service.

[0039] The processing setting unit 11A, as an example, displays the summarization processing setting screen shown in Figure 7 (described later) on the display unit 16 and accepts various settings related to summarization from the user. For example, it is possible to set the number of sentences after summarization, the target language for translation in the case of languages ​​that are not supported for summarization, and whether or not to perform confirmation and correction after summarization.

[0040] The acquisition unit 11B acquires document data written in a certain language. The document data includes documents to be subject to summarization processing and may be either text data or image data. In the case of image data, OCR (Optical Character Recognition) processing is performed to convert it into text data. Specifically, as an example, document data like that shown in Figure 5 is acquired.

[0041] Figure 5 shows an example of document data according to this embodiment. The document data shown in Figure 5 is represented as document data written in "Korean".

[0042] The language determination unit 11C, based on the language described in the document data acquired by the acquisition unit 11B, refers to the unsupported language table 151 shown in Figure 3 above as an example, and determines whether the language described in the document data is an unsupported language that is not compatible with summarization processing. In the example in Figure 5 above, since the document data is in "Korean," it is determined to be an unsupported language from the unsupported language table 151 shown in Figure 3 above. On the other hand, if the document data is in "English" or "Japanese," it is determined to be a supported language from the supported language table 152 shown in Figure 4 above. The type of language described in the document data is determined using, for example, the AWS (Amazon Web Services) Comprehend service or the GCP (Google Cloud Platform) Translation API (Application Programming Interface).

[0043] If the translation processing unit 11D determines that the language is an unsupported language that is not compatible with summarization processing, it translates the document data into a supported language that is compatible with summarization processing. In the example in Figure 5 above, since the document data is written in "Korean," it refers to the unsupported language table 151 shown in Figure 3 above and translates it into "Japanese," which has high affinity with "Korean." Specifically, as an example, it is translated into document data like that shown in Figure 6.

[0044] Figure 6 shows an example of translated document data according to this embodiment. The translated document data shown in Figure 6 is represented as document data written in "Japanese".

[0045] The summarization processing unit 11E performs summarization on translated document data obtained by the translation processing unit 11D through translation into a corresponding language (e.g., Japanese). The summarization processing unit 11E also performs summarization on document data determined by the language determination unit 11C to be in a corresponding language (e.g., Japanese). Existing technologies such as IBM's (registered trademark) summarization service (Watson Natural Language Understanding) and Python's Sumy are used for the summarization process. Document summarization technologies in natural language processing can be broadly divided into two types: extractive and generative. Sumy, mentioned above, is considered an extractive summarization library that uses an algorithm to extract sentences deemed important.

[0046] The retranslation processing unit 11F retranslates the summarized document data obtained by the summarization processing unit 11E into an unsupported language (i.e., the original language, in this case Korean).

[0047] The output unit 11G outputs summarized document data obtained by retranslation by the retranslation processing unit 11F, or summarized document data summarized by the summarization processing unit 11E. Specifically, as an example, the confirmation and correction screen shown in Figure 8, described later, is displayed on the display unit 16.

[0048] Next, with reference to Figure 7, the summary processing settings screen displayed by the processing settings unit 11A will be described in detail. Note that the summary processing settings screen is just one example of a settings screen.

[0049] Figure 7 shows an example of the summary processing settings screen 161 according to this embodiment.

[0050] The summarization processing settings screen 161 shown in Figure 7 is displayed on the display unit 16 according to user operations. The summarization processing settings screen 161 allows users to configure "maximum number of sentences after summarization," "selection of target language for unsupported languages," and "confirmation and correction of summarization results." For "maximum number of sentences after summarization," for example, the importance of sentences in the document is calculated using an extraction algorithm such as LexRank, a function of Sumy, and sentences (up to 3 in the example in Figure 7) are extracted in order of importance. For "selection of target language for unsupported languages," either automatic mode or manual mode can be selected. Automatic mode is a mode that automatically specifies the target language for translation, while manual mode is a mode that allows the user to specify the target language for translation. In automatic mode, the user cannot select a language, and the language is automatically specified according to the unsupported language table 151 shown in Figure 3 above. On the other hand, in manual mode, the user can select a language, and a pull-down menu 161A is displayed. The language selected by the user from the pull-down menu 161A is specified as the target language for translation. The "Confirmation and Correction of Summary Results" setting determines whether or not to display the confirmation and correction screen shown in Figure 8, for example. This confirmation and correction screen will be displayed if the user selects "Yes," and will not be displayed if the user selects "No."

[0051] Figure 8 is a front view showing an example of the confirmation and correction screen 162 according to this embodiment.

[0052] The confirmation and correction screen 162 shown in Figure 8 is displayed on the display unit 16 when "Confirm and correct summary processing" is set to "Yes" in the summary processing setting screen 161 shown in Figure 7 above. The confirmation and correction screen 162 displays the document data before summarization in an unsupported language (e.g., Korean) along with the summarized document data obtained by re-translating the summarized document data in a supported language (e.g., Japanese) into the unsupported language, and is a screen for confirming and correcting the summarized document data. If the confirmation and correction screen 162 is not displayed, only the summarized document data is displayed.

[0053] Next, the operation of the information processing device 10 according to this embodiment will be explained with reference to Figure 9.

[0054] Figure 9 is a flowchart showing an example of the processing flow by the information processing program 15A according to this embodiment.

[0055] First, when the information processing device 10 is instructed to perform document summarization processing, the CPU 11 starts the information processing program 15A and executes the following steps. Note that in the summarization processing setting screen 161 shown in Figure 7 above, "Confirm and correct summary results" is set to "Yes".

[0056] In step S101 of Figure 9, the CPU 11 acquires document data written in a certain language.

[0057] In step S102, the CPU 11 refers, for example, to the unsupported language table 151 shown in Figure 3 or the supported language table 152 shown in Figure 4, to determine whether the language described in the document data is an unsupported language that is not supported for summarization processing. If it is determined to be an unsupported language (positive determination), the process proceeds to step S103. If it is determined not to be an unsupported language, that is, a supported language that is supported for translation processing (negative determination), the process proceeds to step S107.

[0058] In step S103, the CPU 11 translates document data in an unsupported language into a supported language. For example, if the unsupported language is "Korean," it refers to the unsupported language table 151 shown in Figure 3 above and translates it into the supported language, "Japanese."

[0059] In step S104, the CPU 11 performs summarization processing on the translated document data obtained in step S103. Existing technologies such as IBM's (registered trademark) summarization service (Watson Natural Language Understanding) and Python's Sumy are used for the summarization processing.

[0060] In step S105, the CPU 11 re-translates the summarized document data obtained from the summarization process in step S104 into an unsupported language. For example, it re-translates the summarized document data from "Japanese" to "Korean," which is an unsupported language.

[0061] In step S106, the CPU 11 displays the summarized document data obtained by retranslating in step S105 together with the original document data before summarization, and accepts confirmation and correction from the user. Specifically, as an example, it displays the confirmation and correction screen 162 shown in Figure 8 above, and after accepting confirmation and correction from the user, it terminates the series of processes by the information processing program 15A.

[0062] Meanwhile, in step S107, summarization processing is performed on document data written in a corresponding language (e.g., Japanese).

[0063] In step S108, the CPU 11 displays the summarized document data obtained from the summarization process in step S107, along with the original document data before summarization, and accepts user confirmation and corrections. Specifically, as an example, the confirmation and correction screen 162 shown in Figure 8 above is displayed, and after accepting user confirmation and corrections, the series of processes by the information processing program 15A is terminated.

[0064] As described above, according to this embodiment, it is determined whether the language described in the document data is an unsupported language that does not support summarization processing. If it is determined to be an unsupported language, the document data is translated into a supported language that does support summarization processing. Summarization processing is then performed on the translated document data obtained by translating into the supported language. Finally, the summarized document data in the supported language obtained by summarization processing is retranslated back into the unsupported language. This makes summarization processing possible even for documents in languages ​​that do not support summarization processing.

[0065] In each of the above embodiments, the term "processor" refers to a processor in a broad sense, and includes general-purpose processors (e.g., CPU: Central Processing Unit, etc.) and dedicated processors (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

[0066] Furthermore, the processor operations in each of the above embodiments may not be performed by a single processor, but may also be performed by multiple processors located in physically separate locations working together. Also, the order of the processor operations is not limited to the order described in each of the above embodiments, but may be changed as appropriate.

[0067] The above describes an information processing device based on an embodiment. The embodiment may take the form of a program that causes a computer to execute the functions of each part of the information processing device. The embodiment may also take the form of a non-temporary storage medium that is readable by a computer and stores these programs.

[0068] Furthermore, the configuration of the information processing device described in the above embodiment is merely an example, and may be modified as needed without departing from the main purpose.

[0069] Furthermore, the program processing flow described in the above embodiment is just one example, and unnecessary steps may be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0070] Furthermore, although the above embodiment describes a case in which the process according to the embodiment is realized by a software configuration using a computer by executing a program, the embodiment is not limited to this. The embodiment may also be realized by a hardware configuration or a combination of a hardware configuration and a software configuration. [Explanation of symbols]

[0071] 10 Information Processing Devices 11 CPU 11A Processing setting unit 11B Acquisition Department 11C Language judgment section 11D Translation Processing Unit 11E Summary Processing Unit 11F Retranslation Processing Unit 11G output section 12 ROM 13 RAM 14 I / O 15 Storage section 15A Information Processing Program 16 Display section 17 Control section 18 Communications Department 151 Unsupported Language Table 152 Supported Language Table 161 Summary Processing Settings Screen 162 Confirmation / Correction Screen

Claims

1. Equipped with a processor, The aforementioned processor, Determine whether the language used in the document data is a primary language that is not supported for summarization processing. If it is determined that the document data is in the first language, the document data is translated into the second language corresponding to the summarization process. The translated document data obtained by translating into the second language is subjected to the summarization process, The summarized document data in the second language obtained by the summarization process is retranslated into the first language. The processor performs control to display a settings screen that allows the user to set either an automatic mode, which automatically specifies the second language, or a manual mode, which allows the user to specify the second language. Information processing device.

2. The settings screen displays the document data in the first language along with the summarized document data obtained by retranslating it into the first language, and allows the user to configure whether or not to display a confirmation and correction screen for reviewing and correcting the summarized document data. The information processing apparatus according to claim 1.

3. Determine whether the language used in the document data is a primary language that is not supported for summarization processing. If it is determined that the document data is in the first language, the document data is translated into the second language corresponding to the summarization process. The translated document data obtained by translating into the second language is subjected to the summarization process, The summarized document data in the second language obtained by the summarization process is retranslated into the first language. The control system displays a settings screen that allows the user to select either an automatic mode, which automatically specifies the second language, or a manual mode, which allows the user to specify the second language. An information processing program designed to be executed by a computer.

Images