Information processing methods, information processing systems, and programs

Abstract

This invention provides an information processing method, information processing system, and program that yield translation results that better match the intended meaning. [Solution] The information processing method translates a selected text written in a first language to be translated from the first language to a selected second language using machine translation, translates the text translated into the second language back into the first language using machine translation, and outputs a screen including the text translated into the first language using machine translation and a graphical user interface component relating to instructions for machine translation.

Description

Technical Field

[0001] The present invention relates to an information processing method, an information processing system, and a program.

Background Art

[0002] Patent Document 1 discloses a translation device with a simple configuration that enables accurate translation.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is room for improvement in obtaining a more intended translation result.

Means for Solving the Problems

[0005] According to one aspect of the present invention, an information processing method executed by an information processing system is provided. This information processing method causes a selected sentence described in a first language to be translated from the first language to a second language selected using machine translation. The sentence translated into the second language is translated back into the first language using machine translation. A screen including the sentence translated into the first language using machine translation and graphical user interface components related to an instruction for machine translation is output.

Brief Description of the Drawings

[0006] [Figure 1] FIG. 1 is a diagram showing an example of the system configuration of an information processing system. [Figure 2] FIG. 2 is a diagram showing an example of the hardware configuration of a server device. [Figure 3]Figure 3 shows an example of the hardware configuration of a client device. [Figure 4] Figure 4 is a flowchart showing an example of information processing performed by a server device. [Figure 5] Figure 5 shows an example of a screen displayed on the output section of a client device. [Figure 6] Figure 6 shows an example of a translation confirmation screen. [Figure 7] Figure 7 shows an example of the translation results screen. [Figure 8] Figure 8 shows an example of a dictionary registration menu. [Modes for carrying out the invention]

[0007] Embodiments of the present invention will be described below with reference to the drawings. The various features shown in the embodiments below (including modified examples; the same applies hereinafter) can be combined with each other.

[0008] <Embodiment 1> 1. System Configuration Diagram Figure 1 shows an example of the system configuration of the information processing system 1000. As shown in Figure 1, the information processing system 1000 includes a server device 100 and a client device 110 as its system configuration. The server device 100 is an example of a computer. The server device 100 and the client device 110 are connected to each other via a network 150. The network 150 may include either or both a WAN (Wide Area Network) and / or the Internet. The network 150 is configured to allow communication between devices connected to the network 150 via wired and wireless connections. The information processing system 1000 is a system that provides so-called SaaS (Software as a Service) functionality.

[0009] The server device 100 performs information processing, specifically translation-related processing, as described in Embodiment 1, in response to requests from the client device 110. Details of the server device 100's processing will be explained later using flowcharts and the like. The information processing system 1000 may consist of one or multiple server devices. If the information processing system 1000 consists of multiple server devices, the functions of the server device 100 are provided as a so-called distributed system.

[0010] The client device 110 is a device operated by an operator of the information processing system 1000 and utilizes the functions provided by the server device 100. In Figure 1, a PC (Personal Computer) is shown as an example of the client device 110, but it is not limited to a PC; it may also be a tablet terminal or a smartphone. The client device 110 can be any device that can input operator information and display the results of processing in the server device 100.

[0011] Here, the information processing system described in the claims may consist of multiple devices or of a single device. If the information processing system described in the claims consists of a single device, an example of such a device is, for example, a server device 100. If the information processing system described in the claims consists of multiple devices, an example of multiple devices is, for example, a distributed system that provides the functions of the server device 100.

[0012] 2. Hardware Configuration (1) Hardware configuration of server device 100 Figure 2 shows an example of the hardware configuration of server device 100. As shown in Figure 2, the server device 100 includes, as a hardware configuration, a control unit 210, a storage unit 220, a communication unit 230, and an internal bus 240. The control unit 210, the storage unit 220, and the communication unit 230 are electrically connected via the internal bus 240.

[0013] The control unit 210 is a CPU (Central Processing Unit) or the like, and controls the entire server device 100.

[0014] The storage unit 220 is any one of an HDD (Hard Disk Drive), ROM (Read Only Memory), RAM (Random Access Memory), SSD (Solid Sate Drive), or any combination thereof, and stores programs and data (for example, pre-translation text data, post-translation text data, etc.) used when the control unit 210 executes processing based on the programs. Hereinafter, the server device 100 will be described as having a ROM, a RAM, an HDD, and an SSD as the storage unit. The storage unit 220 is an example of a storage medium. In the specification, it is described that data used when the control unit 210 executes processing based on a program is stored in the storage unit 220, but it may be stored in the storage unit of another device communicable with the server device 100. That is, the data may be stored in the storage unit of any device as long as the control unit 210 can refer to or acquire it. By the control unit 210 executing processing based on the program stored in the storage unit 220, the functions of the server device 100 and the processing of the flowchart shown in FIG. 4 described later are realized.

[0015] The communication unit 230 connects the server device 100 to the network 150 and controls communication with other devices.

[0016] (2) Hardware Configuration of the Client Device 110 FIG. 3 is a diagram showing an example of the hardware configuration of the client device 110. As shown in FIG. 3, the client device 110 includes, as a hardware configuration, a control unit 310, a storage unit 320, an input unit 330, an output unit 340, a communication unit 350, and an internal bus 360.

[0017] The control unit 310 is a CPU or the like, and controls the entire client device 110.

[0018] The storage unit 320 is any one of an HDD, a ROM, a RAM, an SSD, etc., or any combination thereof, and stores a program and data used when the control unit 310 executes processing based on the program. The storage unit 320 is an example of a storage medium.

[0019] The input unit 330 is a keyboard, a mouse, etc., and inputs information based on a selection operation and / or an input operation by an operator. The output unit 340 is a display, etc., and displays input information via a screen by an operator, the result of processing by the control unit 310, etc.

[0020] The communication unit 350 connects the client device 110 to the network 150 and controls communication with other devices.

[0021] 3. Information Processing (1) Outline of Processing The control unit 210 uses a trained model to translate a sentence written in a first language to be translated, selected by the client device 110, from the first language to a second language selected by the client device. The trained model may be a trained model that has been trained to translate sentences in a specified language to another specified language, or it may be a so-called large-scale language model that has been trained on a large-scale language model. ChatGPT is an example of a large-scale language model. In this specification, a large-scale language model will be used as the trained model. The large-scale language model may be stored in the storage unit 220 of the server device 100, or it may be implemented in another system. In this specification, the functions of the large-scale language model will be used via the API (Application Programming Interface) of the large-scale language model implemented in another system. The trained model is an example of machine translation. The first language is, for example, Japanese. The second language is, for example, English. The first and second languages ​​may be set in advance, or they may be set via a screen or the like when instructing translation. For the sake of simplicity, the first language will be Japanese and the second language will be English in the following explanation. The control unit 210 uses a trained model to translate the text translated into the second language back into the first language. This type of translation can also be called back-translation. Back-translation is the process of translating a text that has already been translated back into its original language. The control unit 210 outputs a screen containing the text translated into the first language using the trained model (the back-translated text) and graphical user interface components related to instructions for the trained model. Graphical user interface components are also referred to as GUI components. GUI components are visual elements (element images) that can be operated by the user on the screen displayed on the output unit 340 of the client device 110.

[0022] By performing this process, it is possible to check the back-translated text. Furthermore, by checking the back-translated text, it is possible to check the quality of the translation, identify translation errors, and input instructions to the trained model (hereinafter simply referred to as AI) using the GUI components included on the screen.

[0023] (2) Details of the process Figure 4 is a flowchart showing an example of information processing performed by the server device 100. Figure 5 is a diagram showing an example of a screen displayed on the output unit 340 of the client device 110. The client device 110 transmits authentication information entered via a screen or the like to the server device 100. The control unit 210 of the server device 100 authenticates the user based on the entered authentication information. Then, based on a predetermined operation via the screen displayed on the client device 110, the control unit 210 transmits a screen 500 containing the document selected by the user to the client device 110 and controls it to be displayed on the output unit 340. On the screen 500, the user selects the text to be translated by performing a predetermined operation. In the example in Figure 5, text 510 is selected as the text to be translated on the screen 500. That is, the text is the text displayed on the screen. When a text is selected and a predetermined operation is performed (for example, right-clicking on the selected text and selecting "Translate" from the context menu that appears), a translation instruction containing the selected text is transmitted from the client device 110 to the server device 100. The translation instruction includes information for the first language and information for the second language. That is, the translation instruction includes information on which languages ​​are being translated from and to.

[0024] In step S410, the control unit 210 determines whether or not it has received a translation instruction from the client device 110. If the control unit 210 determines that it has received a translation instruction from the client device 110, it proceeds to step S415. If the control unit 210 determines that it has not received a translation instruction from the client device 110, it repeats the process in step S410.

[0025] In step S415, the control unit 210 translates the selected text from the first language to the second language using AI. More specifically, the control unit 210 generates a prompt to translate the selected text from the first language to the second language. The control unit 210 inputs the generated prompt to the AI. For example, the prompt to the AI ​​for translating from the first language to the second language includes category information indicating the category of the text. For example, the control unit 210 classifies the text into groups and determines the category based on the frequency of word occurrences in the document displayed on screen 500. The control unit 210 includes category information indicating the determined category in the prompt and instructs the AI ​​to translate according to the category. With this configuration, translation according to the category is expected.

[0026] As an example of category-based translation, if the category information "investor-oriented document" is included in the prompt, the following process is performed: The control unit 210 obtains the source text of investor-oriented documents such as press releases, financial reports, and annual reports of the company to be translated. Based on label information indicating labels attached to these documents, the control unit 210 confirms that the document belongs to the category "investor-oriented document" and understands that the overall tone and / or expression of the source text is intended to provide clear and reliable information to investors. Next, the control unit 210 generates a prompt to specify the category information "investor-oriented document" for the source text. This prompt may simply be the addition of the category information "investor-oriented document," or it may include a specific definition of what is required of an "investor-oriented document" (for example, "appropriately translate technical terms and financial terms," ​​"maintain accurate grammar and structure, and make the content clear and easy for investors to understand," "do not compromise legal and financial accuracy," etc.). The control unit 210 then causes the AI ​​to perform the translation based on this prompt. Furthermore, categories may include not only those based on the content, subject, topic, or theme of the document, but also other categories related to the nature and / or usage of the document, such as format / style, purpose, target audience, media format, language / region, legal / regulation, etc. Specific examples are given below. Examples of the format / style category include formal business letters and informal emails. Examples of the purpose category include news articles intended for informational purposes and advertising materials intended for persuasion. Examples of the target audience category include product catalogs for general consumers and academic papers for professionals. Examples of the media format category include text-only reports and presentation materials that include images. Examples of the language / region category include marketing materials for a specific country and multilingual international conference materials. Examples of the legal / regulatory category include legally binding contracts and financial reports that comply with specific regulations.

[0027] Furthermore, the control unit 210 may acquire layout information, which is information about the layout of the screen 500. Layout information includes information such as the position, size, arrangement, color, font, and margins of elements (text, images, buttons, etc.) placed on the screen. For example, the control unit 210 may acquire layout information by analyzing the HTML structure of the screen (web page), or it may take a screenshot of the screen, perform image analysis processing (or image recognition processing) on ​​the image, and extract the layout information. The control unit 210 may also include instruction information in the prompt to maintain the screen layout along with the layout information. With such a configuration, it becomes possible to maintain the layout even on screens that include translated text.

[0028] Furthermore, the control unit 210 may acquire formatting information for the text on the screen 500. Formatting information for the text includes information such as font size, type (font), typeface (bold, italics, etc.), line spacing, paragraph alignment, presence or absence of underlining, and text color. For example, if the text is in a predetermined document format (e.g., PDF), the control unit 210 may extract formatting information from the metadata, or it may take a screenshot of the screen and perform image analysis processing (or image recognition processing) on ​​the image to acquire formatting information for the text. The control unit 210 may also include instruction information in the prompt to maintain the formatting of the text along with the formatting information. With such a configuration, it is possible to maintain the formatting even in the translated text.

[0029] The control unit 210 acquires the translated text output from the AI. This translated text is in a second language.

[0030] In step S420, the control unit 210 uses AI to back-translate the text translated into the second language back into the first language. More specifically, the control unit 210 generates a prompt to translate the text translated into the second language back into the first language. The control unit 210 may also include category information in this prompt. The control unit 210 inputs the generated prompt to the AI. The control unit 210 obtains the translated text output by the AI. This translated text is the translated text in the first language.

[0031] In step S425, the control unit 210 generates a translation confirmation screen. In step S430, the control unit 210 sends a translation confirmation screen to the client device 110, causing it to be displayed on the client device 110.

[0032] Figure 6 shows an example of a translation confirmation screen 600. The translation confirmation screen 600 includes text 610, text 620, GUI component group 630, and GUI component 640. Text 610 is the translated text translated from the first language to the second language. That is, the screen also includes the text translated into the second language. Text 620 is the translated text obtained by back-translating the text translated into the second language back into the first language. GUI component group 630 consists of multiple GUI components corresponding to instruction information for translation from the first language to the second language in the AI. GUI component 640 is a text input area into which free-form instructions for translation from the first language to the second language in the AI ​​can be entered.

[0033] The GUI components that make up the GUI component group 630 (in the example in Figure 6, "Make the text more compact," "Use a financial writing style," "Add annotations to technical terms," ​​"Translate again because an element is missing," etc.) can be said to correspond to instruction information given to the trained model. Multiple sets of instruction information are pre-configured (or stored) in the server device 100. The control unit 210 selects instruction information based on the text (or document related to the text) selected on the screen 500. For example, the control unit 210 may select instruction information based on the language or format of the text (article, report, novel, poem, etc.), tone (subjective, objective, formal, informal, etc.), style (colloquial, written, literary, scientific, etc.), length (short text, long text, etc.), subject (science, history, art, etc.), keywords (words that frequently appear in the text), etc. These can also be called categories of text. In other words, the control unit 210 can be said to select instruction information based on the category of text. The control unit 210 displays GUI components corresponding to the selected instruction information on the translation confirmation screen 600. GUI component 640 can be described as a text input area for inputting instruction information to give to the trained model.

[0034] In step S435, the control unit 210 determines whether or not it has received instruction information. The control unit 210 receives instruction information for the AI ​​if a GUI component included in the GUI component group 630 is selected, or if an instruction is entered in the GUI component 640. If a GUI component such as "No problem (reflect this content)" is selected, the control unit 210 determines that it has not received instruction information. If the control unit 210 determines that it has received instruction information, it proceeds to step S440. If the control unit 210 determines that it has not received instruction information, it proceeds to step S445.

[0035] In step S440, the control unit 210 generates a prompt containing instruction information. If a GUI component from the GUI component group 630 is selected on the translation confirmation screen 600, the control unit 210 generates a prompt containing instruction information corresponding to the selected GUI component. For example, if the GUI component "Make it sound like a financial document" is selected on the translation confirmation screen 600, a prompt containing instruction information such as "Please translate it to sound like a financial document" is generated. The instruction information is the instruction information for translating the text from the first language to the second language. If instruction information is entered into the GUI component 640 on the translation confirmation screen 600, the control unit 210 generates a prompt containing the instruction information to be given to the AI, which is entered into the GUI component 640, i.e., the text input area. The instruction information is the instruction information for translating the text from the first language to the second language.

[0036] If the process proceeds from step S440 to step S415, the control unit 210 repeats the processing from step S415 to step 435. That is, based on the prompt, the control unit 210 uses AI to translate the text from the first language to the second language. The control unit 210 uses AI to translate the text translated into the second language back into the first language. The control unit 210 generates a translation confirmation screen including at least the text translated into the first language and GUI components, sends it to the client device 110, and has the client device 110 display it.

[0037] In step S445, the control unit 210 confirms the translation of the selected text and reflects the translated text in the second language on the translation result screen, which is temporarily stored in a predetermined storage area such as the memory unit 220. In step S450, the control unit 210 transmits the translation result screen to the client device 110 and displays it on the client device 110.

[0038] Figure 7 shows an example of the translation result screen 700. The translated text 710 is the translated text of sentence 510. The user can select the text to be translated on screen 500 as shown in Figure 5, check the translated text on translation confirmation screen 600 as shown in Figure 6, input instructions as needed, and have the AI ​​generate an appropriate translation.

[0039] According to the processing in Embodiment 1, a translation result that better matches the intended meaning can be obtained.

[0040] (Variation 1) Modification 1 of Embodiment 1 will now be described. Modification 1 is included in Embodiment 1 and is not different from Embodiment 1. Configurations not described in Modification 1 are the same as in Embodiment 1.

[0041] In Modification 1, the control unit 210 stores a history of instruction information selected or entered on the translation confirmation screen 600 for each user as history information in a predetermined storage area such as the storage unit 220. This is an example of the process by which the control unit 210 stores history information of instructions given to the AI ​​via GUI components. Furthermore, the control unit 210 may generate prompts based on the user's history information and send them to the AI. That is, prompts to the AI ​​for translating from the first language to the second language include instruction information based on the history information.

[0042] According to variation 1, it is possible to obtain translation results that suit the user's preferences.

[0043] (Modification 2) Modification 2 of Embodiment 1 will now be described. Modification 2 is included in Embodiment 1 and is not different from Embodiment 1. Configurations not described in Modification 2 are the same as in Embodiment 1.

[0044] In the modified example 2, the control unit 210 may register words in a document that have been translated from the first language to the second language into a dictionary for each user. The control unit 210 may automatically register words in the first language contained in a document and words in the second language contained in the corresponding finalized translation in a dictionary, associating them with user identification information, or it may register words in the first language contained in a document and words in the second language contained in the corresponding finalized translation in a dictionary, associating them with user identification information, in response to dictionary registration operations via the screen.

[0045] Figure 8 shows an example of the dictionary registration menu 810. The user performs a predetermined operation on a predetermined screen (for example, the translation confirmation screen 600) and selects a word. Then, the dictionary registration menu 810 is displayed, which includes the word in the first language contained in the sentence and the word translated into the second language. When the registration button or the like is selected in the dictionary registration menu 810, the control unit 210 registers the word in the first language contained in the sentence displayed in the dictionary registration menu 810 and the word translated into the second language into the dictionary. The control unit 210 can instruct the AI ​​to translate by including in the prompt an instruction that words registered in the dictionary should be translated as they are registered in the dictionary, along with the dictionary registration data (the word in the first language before translation and the word in the second language after translation).

[0046] According to Modification 2, dictionary registration can be performed according to the user. As a result, by instructing the system to translate based on the words registered in the dictionary, it is possible to expect more accurate translations, improved translation speed, and improved translation quality.

[0047] <Note> This embodiment includes the following disclosures.

[0048] (Note 1) An information processing method performed by an information processing system, A selected text written in the first language to be translated is translated from the first language to the second language selected using machine translation. The text translated into the second language is then translated back into the first language using the machine translation tool. The system outputs a screen that includes the text translated into the first language using the machine translation and a graphical user interface component relating to instructions for the machine translation. Information processing methods. (Note 2) The information processing method described in Appendix 1, The graphical user interface component corresponds to the instruction information that instructs the machine translation, Generate a prompt containing instruction information corresponding to the selected graphical user interface component. The aforementioned instruction information is instruction information for translating the text from the first language to the second language. Information processing methods. (Note 3) The information processing method described in Appendix 1, The graphical user interface component includes a text input area for inputting instruction information to instruct the machine translation, A prompt is generated that includes instruction information to be used to instruct the machine translation, which is entered in the text input area. The aforementioned instruction information is instruction information for translating the text from the first language to the second language. Information processing methods. (Note 4) An information processing method described in any one of the appendices 1 to 3, The aforementioned screen also includes the aforementioned text translated into the second language. Information processing methods. (Note 5) The information processing method described in Appendix 2 or Appendix 3, Based on the prompt, the text is translated from the first language to the second language using the machine translation tool. The text translated into the second language is then translated back into the first language using the machine translation tool. The system outputs a screen that includes the text translated into the first language and the graphical user interface components. Information processing methods. (Note 6) An information processing method described in any one of the items from Appendix 1 to Appendix 5, The above text is the text displayed on the screen. The prompt for the machine translation to translate from the first language to the second language includes instruction information to maintain the screen layout of the text. Information processing methods. (Note 7) An information processing method described in any one of the items from Appendix 1 to Appendix 6, The prompt for the machine translation to translate from the first language to the second language includes category information indicating the category of the text. Information processing methods. (Note 8) The information processing method described in Appendix 2, Multiple instruction pieces are set in advance. Based on the above text, select the above instruction information, A graphical user interface component corresponding to the selected instruction information is displayed on the screen. Information processing methods. (Note 9) The information processing method described in Appendix 8, Select the instruction information based on the category of the aforementioned text. Information processing methods. (Note 10) An information processing method described in any one of the items from Appendix 1 to Appendix 9, The system stores historical information of instructions for machine translation via the graphical user interface component. The prompt for the machine translation to translate from the first language to the second language includes instruction information based on the history information. Information processing methods. (Note 11) An information processing method described in any one of the items from Appendix 1 to Appendix 10, The prompts for the machine translation to translate from the first language to the second language include instruction information to maintain the formatting of the document. Information processing methods. (Note 12) An information processing method described in any one of the items from Appendix 1 to Appendix 11, The words included in the aforementioned text, translated from the first language to the second language, are registered in the dictionary. Information processing methods. (Note 13) An information processing system, Having at least one control unit, The control unit, A selected text written in the first language to be translated is translated from the first language to the second language selected using machine translation. The text translated into the second language is then translated back into the first language using the machine translation tool. The system outputs a screen that includes the text translated into the first language using the machine translation and a graphical user interface component relating to instructions for the machine translation. Information processing system. (Note 14) It is a program, On the computer, A program for executing the information processing method described in any one of the appendices 1 through 12.

[0049] Although embodiments have been described above, these are presented as examples and are not intended to limit the scope of the invention. Novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of Symbols]

[0050] 100: Server device 110: Client device 150: Network 210: Control Unit 220: Storage section 230: Communications Department 1000: Information Processing System

Claims

1. An information processing method performed by an information processing system, A selected text written in the first language to be translated is translated from the first language to the selected second language using machine translation. The text translated into the second language is then translated back into the first language using the machine translation tool. The system outputs a screen that includes the text translated into the first language using the machine translation and a graphical user interface component relating to instructions for the machine translation. Information processing methods.

2. The information processing method according to claim 1, The graphical user interface component corresponds to the instruction information that instructs the machine translation, Generate a prompt containing instruction information corresponding to the selected graphical user interface component. The aforementioned instruction information is instruction information for translating the text from the first language to the second language. Information processing methods.

3. The information processing method according to claim 1, The graphical user interface component includes a text input area for inputting instruction information to instruct the machine translation, A prompt is generated that includes instruction information to be used to instruct the machine translation, which is entered in the text input area. The aforementioned instruction information is instruction information for translating the text from the first language to the second language. Information processing methods.

4. The information processing method according to claim 1, The aforementioned screen also includes the aforementioned text translated into the second language. Information processing methods.

5. The information processing method according to claim 2, Based on the prompt, the text is translated from the first language to the second language using the machine translation tool. The text translated into the second language is then translated back into the first language using the machine translation tool. The system outputs a screen that includes the text translated into the first language and the graphical user interface components. Information processing methods.

6. The information processing method according to claim 1, The above text is the text displayed on the screen. The prompt for the machine translation to translate from the first language to the second language includes instruction information to maintain the screen layout of the text. Information processing methods.

7. The information processing method according to claim 1, The prompt for the machine translation to translate from the first language to the second language includes category information indicating the category of the text. Information processing methods.

8. The information processing method according to claim 2, Multiple instruction pieces are set in advance. Based on the above text, select the above instruction information, A graphical user interface component corresponding to the selected instruction information is displayed on the screen. Information processing methods.

9. The information processing method according to claim 8, Select the instruction information based on the category of the aforementioned text. Information processing methods.

10. The information processing method according to claim 1, The system stores historical information of instructions for machine translation via the graphical user interface component. The prompt for the machine translation to translate from the first language to the second language includes instruction information based on the history information. Information processing methods.

11. The information processing method according to claim 1, The prompts for the machine translation to translate from the first language to the second language include instruction information to maintain the formatting of the document. Information processing methods.

12. The information processing method according to claim 1, The words included in the aforementioned text, translated from the first language to the second language, are registered in the dictionary. Information processing methods.

13. An information processing system, Having at least one control unit, The control unit, A selected text written in the first language to be translated is translated from the first language to the selected second language using machine translation. The text translated into the second language is then translated back into the first language using the machine translation tool. The system outputs a screen that includes the text translated into the first language using the machine translation and a graphical user interface component relating to instructions for the machine translation. Information processing system.

14. It is a program, On the computer, A program for causing the information processing method described in any one of claims 1 to 12.

Images