Reading comprehension support methods

Abstract

This system or method provides a reading comprehension support system that allows natural language input as query text and presents the reader with sections of the text that are highly relevant to the input text. [Solution] The reading support system includes a document reading unit 101 that reads the target document, a block division unit 103 that divides the target document into multiple blocks, a distributed representation acquisition unit 104a that acquires word distributed representations for each of the multiple blocks, a question input unit 102 that reads the question, a distributed representation acquisition unit 104b that extracts words contained in the question and acquires word distributed representations, and a similarity calculation unit 106 that compares the word distributed representations in the question and each of the multiple blocks and calculates the similarity. The similarity calculation unit searches for words that match words contained in the question from among the words contained in the block, and for the matching words, it calculates the similarity between the word distributed representation in the block and the word distributed representation in the question.

Description

Technical Field

[0001] One aspect of the present invention relates to a document reading support system and a reading support method.

Background Art

[0002] When reading a document, the way of reading the document varies depending on the purpose of the reader, the type and nature of the document. Sometimes the entire document is read, and sometimes the purpose is to search for information necessary for the reader. In such a case, it is sufficient to search for the location where the necessary information is described in the document and only glance at the relevant location. As a method of searching for necessary information in a document, there is a method of using a table of contents or an index. For an electronic document, there is also a method of searching for desired information by searching with a keyword word. In addition, a method of performing structural analysis of a document according to set rules has been proposed (Patent Document 1).

[0003]

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

[0005] When using a table of contents or index, the word you want to find is used directly in the table of contents or index. Without it, efficiency suffers. By searching the text using keywords, keywords can be found throughout the entire document. It is possible to search for sentences or paragraphs containing the keyword, but it may not always be efficient in finding the desired information. The reason why it's not easy to find is that there are too many results for the keyword. It takes too long to find the information; a single keyword isn't enough to narrow down the desired information. Reasons for not finding a suitable keyword include: not having one, or being unable to find a suitable keyword. Also, the document follows the rules. When performing structural analysis, the structure to be read is limited, so sentences with various structures It is difficult to handle the writing. One aspect of the present invention solves at least one of these problems. It is.

[0006] One aspect of the present invention enables natural language input as a query sentence, and the input sentence is associated with The objective is to provide a reading comprehension support system or method that presents the reader with the most important sections of the text. This will be one of the topics.

[0007] Furthermore, the description of these problems does not preclude the existence of other problems. One aspect of the present invention is It is not necessarily required to resolve all of these issues. Specifications, drawings, invoices. It is possible to extract other issues from the descriptions in the sections. [Means for solving the problem]

[0008] One aspect of the present invention is a document reading unit that reads a target document, and a unit that divides the target document into multiple blocks. The first distribution obtains word embeddings for each of the multiple blocks in the document segmentation unit. Expression acquisition unit, query text reading unit that reads the query text, words contained in the query text A second distributed representation acquisition unit extracts and obtains word distributed representations, and a query text and multiple A similarity retrieval unit compares the word embeddings with each block and calculates the similarity. It is a reading comprehension support system. The similarity acquisition unit selects the words contained in the block from the quest. Search for words that match the words contained in the text, and for the matching words, place them in a block. The similarity between the word embeddings in the query text and the word embeddings in the query text is calculated.

[0009] One aspect of the present invention involves the steps of reading a target document and dividing the target document into multiple blocks. Steps include obtaining word embeddings for each of multiple blocks, and quests. The process involves reading the text, extracting words from the query text, and obtaining word embeddings. The steps involve the query statement and each of the multiple blocks, and the word embeddings. This reading comprehension support method includes a step of comparing and determining similarity. In this step, the program searches for words within a block that match the words in the query sentence. The search results show the word embeddings in the block and the query text for matching words. We calculate the similarity between the word and its embedded representation.

[0010] Each block may contain one or more paragraphs from the document in question.

[0011] Each block can contain one or more statements.

[0012] Similarity scores may be obtained only for specific parts of speech.

[0013] The similarity may be obtained by calculating the cosine similarity.

[0014] When there are multiple words that match between the query sentence and the block, the sum of the dispersion representations of each word of the similarity may be used as the score for the block.

Advantages of the Invention

[0015] According to one aspect of the present invention, it is possible to provide a reading comprehension support system or a reading comprehension support method that enables input of natural language as a query sentence and presents to a reader a portion highly relevant to the input sentence. Note that the description of these effects does not prevent the existence of other effects. One aspect of the present invention

[0016] does not necessarily have to have all of these effects. It is possible to extract other effects from the description of the specification, drawings, and claims.

Brief Description of the Drawings

[0017] [Figure 1] [Figure 2] FIG. 1 is a diagram showing an example of a reading comprehension support system. [Figure 3] FIG. 2 is a flowchart showing an example of a reading comprehension support method. [Figure 3] FIG. 3 is a flowchart showing an example of a reading comprehension support method. [Figure 4] FIG. 4 is a diagram for explaining the distributed representation of words. [Figure 5] FIG. 5 is a diagram for explaining an example of a similarity calculation method. [Figure 6] FIG. 6 is a diagram showing an example of the hardware of a reading comprehension support system. [Figure 7] FIG. 7 is a diagram showing an example of the hardware of a reading comprehension support system.

Modes for Carrying Out the Invention

[0018] Embodiments will be described in detail with reference to the drawings. However, the present invention is not limited to the following description. Without departing from the spirit and scope of the present invention, its form and details may be modified in various ways. It will be easily understood by those skilled in the art to obtain this. Therefore, the present invention is as shown in the embodiments below. The interpretation is not limited to the content stated herein.

[0019] In the configuration of the invention described below, the same part or part having a similar function is included. The same reference numerals are used consistently across different drawings, and explanations of their repetition are omitted. When referring to the function of [this], the hatch pattern is the same, and sometimes no specific symbol is assigned.

[0020] Furthermore, the position, size, and scope of each component shown in the drawings are, for the sake of ease of understanding, actually The location, size, and range may not be described. Therefore, the disclosed invention must always Furthermore, it is not limited to the location, size, scope, etc., disclosed in the drawings.

[0021] (Embodiment 1) In this embodiment, a reading comprehension support system and a reading comprehension support method according to one aspect of the present invention are shown in Figures 1- This will be explained using Figure 5.

[0022] In the reading comprehension support method of this embodiment, first, the user selects the document they want to read (the target document), and The system retrieves documents (query statements) related to the information that the system needs. The target documents are multiple. The text is divided into blocks (e.g., paragraphs), and word embeddings are obtained for each block. Obtain the embedded representations of the words contained in the text. Next, from the words contained in the block... Then, it searches for words that match the words contained in the query text. And for the matching words... The similarity between word embeddings in a block and word embeddings in the query text. For example, calculate cosine similarity. If there are multiple matching words, calculate each word. The sum of the similarities of the distributed representations is taken as the block score. Blocks with relatively high scores are Therefore, it is considered to have a high degree of relevance to the query text. This indicates a relationship or Sections with high similarity can be displayed from the target document. For example, sorted by score. The blocks of the target document can be arranged and presented in order of relevance.

[0023] In this embodiment of the reading comprehension support method, by inputting a question in natural language, the system selects from the target documents. It is possible to point to the relevant section of the question. Even the same word can appear differently depending on the context. Because distributed representations are used, blocks with a higher relationship or similarity to the question are presented. It is possible.

[0024] The question can contain one or more sentences. The selection of keywords to use in the search is important. Because it is essential, users can find the desired information from the document with minimal effort.

[0025] Unless otherwise specified in this specification, a document is a description of an event in natural language, and electricity The documents are childized and machine-readable. Examples include patent applications, case law, contracts, terms and conditions, and product information. This includes, but is not limited to, manuals, novels, publications, white papers, and technical documents. In this specification, etc., "text" includes one or more sentences.

[0026] In this specification, a word is the smallest linguistic unit that possesses a sound, meaning, and grammatical function. However, we may also seek embedded representations for subwords obtained by further dividing a word. For example, English The word "transformer" is a combination of "transform" and "er". It is also possible to decompose it into broaders and assign a distributed representation to each. Or, two or more broaders. It is also possible to assign distributed representations to linked phrases of words. In this specification, a subword obtained by splitting a word is also called a word. The given phrase, word, or subword is sometimes also called a token.

[0027] In this embodiment, even if the word is the same word, the distribution of surrounding words is also Alternatively, it can be obtained using a language model that yields different distributed representations depending on the context. It is obtained using a language model that can produce different distributed representations depending on the context, even for single words. As word embeddings, the position of a word in a sentence and its segment (information about the connection between words in a sentence) A language model can be used that provides a distributed representation with embedded token information. A language model with attention-grabbing capabilities that learns from both sides of text and acquires distributed representations. You may also use "ru". Even the same word can have different meanings depending on the distribution of surrounding words or the context. One example of a language model that can produce dispersive representations is BERT (Bidirectional En). coder Representations from Transformers) (See Non-Patent Document 1) can be cited.

[0028] Figure 4 shows the results for six English sentences containing "carbon" in each sentence. The distributed representation of "carbon" obtained by BERT is plotted on the XY coordinate system. Therefore, the three plots (squares) on the left half contain "carbon" as an impurity in the material. The text is written in a way that the three plots (diamonds) on the right half represent "carbo" as the negative electrode material. This is a text about "n". Figure 4 shows that even though it is the same "carbon", the context and sentence can differ. This is an example demonstrating that different distributed representations can be obtained.

[0029] Even the same word can have different word embeddings depending on the context in which it appears. By using this method, blocks highly relevant to the information the user needs can be displayed with high accuracy. It can be found. For example, if the query text contains "carbon" as a negative electrode material... If this was the case, the score of the block containing "carbon" as the negative electrode material would be Conversely, the score of blocks containing "carbon" as an impurity is relatively high. It is expected to decrease in proportion.

[0030] [Reading comprehension support system] Figure 1 is a block diagram showing the configuration of the reading comprehension support system 100.

[0031] The reading comprehension support system 100 is an information processing system such as a personal computer used by the user. It may be installed in the location. Alternatively, the processing unit of the reading comprehension support system 100 may be installed on the server. Alternatively, it may be configured so that it is accessed and used from a client PC via the network.

[0032] The reading comprehension support system 100 consists of a document reading unit 101, a question input unit 102, and a block division unit 1 03, Distributed representation acquisition unit 104a, Distributed representation acquisition unit 104b, Word selection unit 105, Similarity calculation It comprises an output unit 106, a score display unit 107, and a text display unit 108.

[0033] The document reading unit 101 reads the document to be read.

[0034] The document read by the document reading unit 101 is stored on the personal computer used by the user. It can be a document that has been written, or a document that is stored on network-connected storage. That's good too.

[0035] The question input section 102 is where the user enters the text they specify for the search.

[0036] The method for inputting a question (also called a query text) is to directly enter any text, or You may also copy and paste text from a document file. A portion of the document read by 101 is arbitrarily selected by the user and loaded into the question input unit 102. A mechanism that allows this would also be acceptable.

[0037] The block division unit 103 divides the read document into blocks. This can be called a document division section.

[0038] Divide each paragraph into blocks, treating each sentence separated by a period as a block. The text may be divided into sections, or into blocks of a predetermined number of paragraphs or sentences. Depending on the type, there are documents that have paragraph numbers included from the beginning, and those paragraph numbers Therefore, it may be divided into blocks.

[0039] The distributed representation acquisition unit 104a processes the document read by the document reading unit 101 block by block. Then, obtain the embedded representations of the words contained in the block.

[0040] The distributed representation acquisition unit 104b generates a distributed representation of the words contained in the text entered into the question input unit 102. Acquire the current.

[0041] The distributed representation acquisition unit 104a and the distributed representation acquisition unit 104b basically use the same language model. It is preferable.

[0042] The word selection unit 105 selects words from the input question text to be used for calculating similarity. This is the part that does that.

[0043] Select all words, select specific parts of speech such as nouns, or allow the user to freely select words. You may choose to select at least one word, and even if you select only one word, it may be important to consider the context of the sentence. Because different distributed representations can be obtained, scoring is possible.

[0044] The similarity calculation unit 106 uses the data obtained by the distributed representation acquisition unit 104a and the distributed representation acquisition unit 104b. The similarity of each block to the question sentence is calculated using word embeddings. Similarity calculation Section 106 can be called the similarity acquisition section.

[0045] The score display unit 107 can display the score calculated by the similarity calculation unit 106. .

[0046] The document display unit 108 can display the document read by the document reading unit 101. The display unit 108 may also display the text entered into the question input unit 102.

[0047] It is preferable that the score display unit 107 and the text display unit 108 are synchronized. For example, the score Sort the text blocks in descending order of score, displaying only blocks with a score above a specified value. The display method for the target document may be changed based on the score value, etc.

[0048] [Methods for supporting reading comprehension] Figures 2 and 3 illustrate the flow of processing performed by the reading comprehension support system 100, respectively. This is a diagram. In other words, Figures 2 and 3 are diagrams illustrating a method of reading comprehension support according to one embodiment of the present invention. This could be considered a flowchart illustrating an example of the law.

[0049] [Step S1: Obtain the target document] First, the document to be read is read by the document reading unit 101 of the reading support system 100.

[0050] [Step S2: Divide the target document into multiple blocks] Next, the block division unit 103 divides the target document into multiple blocks.

[0051] [Step S3: Obtain word embeddings for each block] Next, the distributed representation acquisition unit 104a receives text block by block and acquires distributed representations of words. Specifically, the target document is input into a language model such as BERT block by block, and the words are divided... Obtain the scattered representation.

[0052] [Step S4: Retrieve the query statement] Furthermore, the question input unit 102 of the reading comprehension support system 100 retrieves the query text. The text can be anything the user enters, and it should be in the section of the document that is of high interest to the user. The text may also be written in the place. In Figure 2, step S3 is followed by step S4 and step S An example of performing step 5 is shown, as shown in Figure 3, with steps S1 to S3 and step S4 Step S5 and Step S5 can be performed independently, and the order does not matter.

[0053] [Step S5: Obtain word embeddings from the query text] Next, the distributed representation acquisition unit 104b receives a query sentence and acquires word distributed representations. In practice, the query text is input into a language model such as BERT, and word embeddings are obtained. .

[0054] [Step S6: Calculate the block score] Next, the similarity calculation unit 106 calculates the words included in each block and the words included in the query text. It searches for matching words between them, and only if a word matches, it connects the distributed representations of the matching word. By calculating the sine similarity and then summing the cosine similarities within the block, the block's size is determined. Obtain the core.

[0055] In the word selection unit 105, select the words from the query text to be used for similarity calculation. Furthermore, similarity calculations may be performed only for the selected words.

[0056] In this embodiment, we show an example of calculating similarity using cosine similarity, but other similarity A method for calculating degrees may also be used.

[0057] Figure 5 explains how to calculate the score for each block. In Figure 5, the query text is Here is an example of comparing Block 1, Block 2, Block 3, and Block 4 of the target document. To demonstrate, first, search for words in each block of the target document that match the words in the query sentence. For the words that are selected, the cosine similarity of the distributed representation of that word is calculated. If there are multiple matching words in the result, the cosine similarity of each word is added together. Then, the score for that block is calculated. For example, in block 1 shown in Figure 5, the query statement is Two words, word W1 and word W2, match. In this case, the score for block 1 is the same as word W1. This is the sum of the sine similarity and the cosine similarity of word W2.

[0058] [Step S7: Output the calculated score] Then, the blocks with the highest calculated scores are the blocks that are most likely to contain the information you are looking for. This can then be presented to the user.

[0059] As described above, in the reading comprehension support system and reading comprehension support method of this embodiment, the user is able to read... When the document to be analyzed and the text related to the information needed are supplied, the following will be considered within that document: It can present blocks that are highly relevant to the information the user needs. This eliminates the need for keyword selection, making it easier to find desired information within documents.

[0060] In the reading comprehension support system and reading comprehension support method of this embodiment, even if the same word is included, A language model is used that yields different word embeddings depending on the text. It can find blocks that are highly relevant to the information that the user needs, with high accuracy.

[0061] This embodiment can be appropriately combined with other embodiments. Furthermore, this specification Furthermore, if multiple configuration examples are shown within a single embodiment, the configuration examples may be combined as appropriate. It is possible to do so.

[0062] (Embodiment 2) In this embodiment, a reading comprehension support system according to one aspect of the present invention will be explained using Figures 6 and 7. I will reveal it.

[0063] The reading comprehension support system of this embodiment uses the reading comprehension support method shown in Embodiment 1 to read documents This allows for easy searching and retrieval of desired information.

[0064] <Example of a reading comprehension support system configuration 1> Figure 6 shows a block diagram of the reading comprehension support system 200. Note that the drawings attached to this specification are... This classifies the components by function and shows them as independent blocks in a block diagram. However, it is difficult to completely separate the actual components by function, and one component is complex It may also be related to the function of numbers. Furthermore, one function may be related to multiple components. For example, the processing performed by the processing unit 120 is executed on different servers depending on the processing. Sometimes.

[0065] The reading comprehension support system 200 has at least a processing unit 120. The reading comprehension support system shown in Figure 6 The stem 200 further comprises an input unit 110, a storage unit 130, a database 140, and a display unit 1 It has 50 and a transmission line 160.

[0066] [Input section 110] The input unit 110 receives a question sentence (query text) from outside the reading comprehension support system 200. Furthermore, the input unit 110 receives the target document from outside the reading comprehension support system 200. Alternatively, the target document and query text supplied to the input unit 110 are transmitted via the transmission line 160. It is supplied to the processing unit 120, the storage unit 130, or the database 140 via this.

[0067] The target documents and query statements include, for example, text data, audio data, or image data. The data is entered in this format. Preferably, the target document is entered as text data.

[0068] Query text can be entered using a keyboard, touch panel, or other key input methods. Force, voice input using a microphone, reading from recording media, scanner, camera, etc. Examples include image input and data acquisition using communication.

[0069] Even though the reading comprehension support system 200 has a function to convert audio data into text data, That's fine. For example, the processing unit 120 may have that function. Or, a reading comprehension support system. The 200 may further have a voice conversion unit having the said function.

[0070] The reading comprehension support system 200 may have optical character recognition (OCR) functionality. It can recognize characters contained in image data and create text data. For example Alternatively, the processing unit 120 may have the function. Or, the reading comprehension support system 200 may have the function. Furthermore, it may have a character recognition unit that has the said function.

[0071] [Processing step 120] The processing unit 120 receives data supplied from the input unit 110, storage unit 130, database 140, etc. It has the function of performing calculations using data. The processing unit 120 stores the calculation results in the storage unit 130. It can be supplied to the database 140, the display unit 150, and the like.

[0072] The processing unit 120 has the function of dividing a document into multiple blocks. For example, it divides a document into chapters. Even if it has a function to divide into multiple blocks, such as paragraphs or every specified number of sentences, good.

[0073] The processing unit 120 has the function of obtaining word embeddings. For example, blocks of the target document It is possible to obtain embedded representations of words contained within the query text, as well as words contained within the query text.

[0074] The processing unit 120 has the function of extracting words from the query text. You can select which words from the list to use for calculating similarity.

[0075] The processing unit 120 has the function of calculating the similarity between word embeddings.

[0076] The processing unit 120 may use a transistor having a metal oxide in the channel formation region. Because the transistor has an extremely low off-current, it can be used as a memory element. By using it as a switch to hold the charge (data) that has flowed into a capacitive element, This ensures that data retention can be maintained for a long period. Processing unit 120 utilizes this characteristic. By using it in at least one of the registers and cache memory, when necessary The processing unit 120 is operated only in this case, and in other cases, the information from the previous processing is saved to the memory element. By doing so, the processing unit 120 can be turned off. In other words, normally off computer This enables routing and allows for lower power consumption in the reading comprehension support system.

[0077] In this specification, a transistor using an oxide semiconductor in the channel formation region is referred to as O xide Semiconductor transistor, also called OS transistor. The channel formation region of the OS transistor preferably has a metal oxide.

[0078] The metal oxide in the channel-forming region preferably contains indium (In). If the metal oxide in the Nell-forming region is an indium-containing metal oxide, the OS Transis The carrier mobility (electron mobility) of the ion becomes higher. Also, the metallic acid present in the channel-forming region The oxide is preferably an oxide semiconductor containing element M. Element M is aluminum (Al). It is preferable that it be gallium (Ga) or tin (Sn). Other applicable elements M The elements include boron (B), silicon (Si), titanium (Ti), iron (Fe), and nickel. Kel (Ni), Germanium (Ge), Yttrium (Y), Zirconium (Zr), Mo Ribdenum (Mo), Lanthanum (La), Cerium (Ce), Neodymium (Nd), Hafniu Examples include fluorine (Hf), tantalum (Ta), and tungsten (W). However, as element M... In some cases, it is acceptable to combine multiple of the aforementioned elements. Element M, for example, can be combined with oxygen. It is an element with high bonding energy. For example, its bonding energy with oxygen is higher than that of indium. It is an element. Furthermore, the metal oxides that the channel-forming region contains include zinc (Zn). This is preferable. Zinc-containing metal oxides may be prone to crystallization.

[0079] The metal oxides present in the channel-forming regions are not limited to indium-containing metal oxides. The semiconductor layer is made of materials such as zinc tin oxide and gallium tin oxide, which do not contain indium. These included metal oxides containing zinc, metal oxides containing gallium, and metal oxides containing tin. That's fine.

[0080] Furthermore, the processing unit 120 may use a transistor that includes silicon in its channel formation region. stomach.

[0081] Furthermore, the processing unit 120 includes a transistor containing an oxide semiconductor in the channel formation region, and a channel A transistor containing silicon in the flannel formation region may be used in combination with the other transistor.

[0082] The processing unit 120 is, for example, an arithmetic circuit or a central processing unit (CPU). It has an processing unit, etc.

[0083] The processing unit 120 includes a DSP (Digital Signal Processor) and a GP (Ground Processing Unit). It has a microprocessor such as U (Graphics Processing Unit). It is acceptable to do so. Microprocessors are FPGAs (Field Programmable Arrays). Field Programmable Array), FPAA (Field Programmable A Programmable Logic Dev (PLD) such as a rectangular array The configuration may be implemented by ice. The processing unit 120 is determined by the processor. By interpreting and executing instructions from various programs, various data processing and programmatic processes are performed. It is possible to perform the action. The programs that can be executed by the processor are those that the processor possesses. It is stored in at least one of the memory area and the storage unit 130.

[0084] The processing unit 120 may have main memory. The main memory may be volatile memory such as RAM. It has at least one of Mori and non-volatile memory such as ROM.

[0085] For example, RAM can be DRAM (Dynamic Random Access Memory). mory), SRAM (Static Random Access Memory), etc. This is used, and a memory space is virtually allocated and used as the workspace for the processing unit 120. The operating system and application programs stored in the memory unit 130. Program modules, program data, and lookup tables are used for execution. These are then loaded into RAM. These data, programs, and programs loaded into RAM are then loaded into RAM. Each program module is directly accessed and operated by the processing unit 120.

[0086] The ROM contains BIOS (Basic Input / Output) which does not require rewriting. It can store the System and firmware, etc. As for ROM, SCRROM, OTPROM (One Time Programmable Read) Only Memory), EPROM (Erasable Programmable Examples include Read Only Memory. EPROMs include ultraviolet light UV-EPROM (Ultra-Violet) enables the erasure of stored data by irradiation. Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmability) Examples include Read Only Memory (e) and flash memory.

[0087] [Storage section 130] The memory unit 130 has the function of storing the program to be executed by the processing unit 120. The memory unit 130, for example, receives the calculation results generated by the processing unit 120 and the input input to the input unit 110. It may also have a function to store the collected data.

[0088] The storage unit 130 has at least one of volatile memory and non-volatile memory. The unit 130 may have, for example, volatile memory such as DRAM or SRAM. Part 130 is, for example, ReRAM (Resistive Random Access). Memory (also called resistive random-access memory), PRAM (Phase change R) andom Access Memory), FeRAM (Ferroelectric Random Access Memory), MRAM (Magnetoresis (also known as magnetically resistive random access memory) Alternatively, it may have non-volatile memory such as flash memory. Also, storage unit 130 These include hard disk drives (HDDs) and solid-state drives. Recording media such as state drives (Solid State Drive: SSD) It's okay to have live performances.

[0089] [Database 140] The reading comprehension support system may have a database 140. For example, database 1 40 has the function of storing multiple documents. For example, stored in database 140 Using one of the documents as the target document, the reading support method according to one aspect of the present invention is used to read the said document. This can be done. Note that the storage unit 130 and the database 140 are separated from each other. It is not necessary. For example, a reading comprehension support system is a dual system of memory unit 130 and database 140. It may have a memory unit that has the function of one of the following.

[0090] Furthermore, the memory of the processing unit 120, the storage unit 130, and the database 140 is Therefore, it can be considered an example of a non-temporary computer-readable storage medium.

[0091] [Display section 150] The display unit 150 has the function of displaying the calculation results from the processing unit 120. Unit 150 has the function of displaying the target document. The display unit 150 also displays the query text. It may have the function of doing so.

[0092] The reading comprehension support system 200 may also have an output unit. The output unit outputs data externally. It has the function of supplying.

[0093] [Transmission path 160] The transmission line 160 has the function of transmitting various data. Input unit 110, processing unit 120, Data transmission and reception between the memory unit 130, the database 140, and the display unit 150 are performed via transmission path 1 This can be done via 60. For example, data such as the target document can be transmitted via transmission line 160. And then it is sent and received.

[0094] <Example of a reading comprehension support system configuration 2> Figure 7 shows a block diagram of the reading comprehension support system 210. The reading comprehension support system 210 is a system that supports... It has a base 220 and a terminal 230 (such as a personal computer).

[0095] The server 220 includes a communication unit 161a, a transmission line 162, a processing unit 120, and a storage unit 170. Although not shown in Figure 7, the server 220 may also have input / output units, etc. .

[0096] Terminal 230 includes a communication unit 161b, a transmission line 164, a processing unit 180, a storage unit 130, and a display. It has a section 150. Although not shown in Figure 7, the terminal 230 further has a database, etc. It is acceptable to have it.

[0097] The user of the reading comprehension support system 210 enters the question (query text) into the input unit 110 of the terminal 230. Enter the following: The question is sent from the communication unit 161b of terminal 230 to the communication unit 161 of server 220. It will be sent to the video.

[0098] The question received by the communication unit 161a is stored in the storage unit 170 via the transmission line 162. Alternatively, the question may be supplied directly from the communication unit 161a to the processing unit 120.

[0099] The block partitioning, distributed representation acquisition, and similarity calculation described in Embodiment 1 are, respectively, High processing power is required. The processing unit 120 of the server 220 is located in the terminal 230. It has higher processing power compared to processing unit 180. Therefore, these processes are, respectively, It is preferable to perform this at 120.

[0100] Then, the processing unit 120 calculates the score of the block. The score is calculated based on the transmission line 162. The score is stored in the memory unit 170 via [a certain method]. Alternatively, the score is transmitted directly from the processing unit 120 via [a certain method]. The score may be supplied to unit 161a. The score is sent from the communication unit 161a of server 220 to terminal 23. The data is transmitted to communication unit 161b of terminal 0. The score is displayed on the display unit 150 of terminal 230.

[0101] [Transmission lines 162 and 164] Transmission lines 162 and 164 have the function of transmitting data. Communication unit 161a, processing Data transmission and reception between the processing unit 120 and the storage unit 170 are performed via the transmission line 162. This is possible. Input unit 110, communication unit 161b, processing unit 180, storage unit 130, and display unit 1 Data transmission and reception between 50 can be performed via the transmission line 164.

[0102] [Processing Unit 120 and Processing Unit 180] The processing unit 120 uses the data supplied from the communication unit 161a and the storage unit 170, etc. It has the function of performing calculations. The processing unit 180 consists of a communication unit 161b, a storage unit 130, and a display unit. It has the function of performing calculations using data supplied from 150, etc. Processing unit 120 and The processing unit 180 can refer to the description of the processing unit 120. The processing unit 120 is compared to the processing unit 180. High processing capacity is preferable in all aspects.

[0103] [Storage section 130] The memory unit 130 has the function of storing the program to be executed by the processing unit 180. The memory unit 130 contains the calculation results generated by the processing unit 180, the data input to the communication unit 161b, It also has a function to store data entered into the input unit 110.

[0104] [Storage section 170] The storage unit 170 stores multiple documents, calculation results generated by the processing unit 120, and the communication unit 161a. It has a function to store input data and other information.

[0105] [Communication section 161a and communication section 161b] Using communication units 161a and 161b, data is exchanged between the server 220 and the terminal 230. It can send and receive data. Communication units 161a and 161b include a hub and a log A router, modem, etc. can be used. Data can be transmitted and received using either a wired connection or wireless (e.g.) For example, radio waves, infrared rays, etc. may be used.

[0106] This embodiment can be combined with other embodiments as appropriate. [Explanation of symbols]

[0107] W1: word, W2: word, 1: block, 2: block, 3: block, 4: block, 100: Reading comprehension support system, 101: Document reading unit, 102: Question input unit, 103: Block 104a: Distributed representation acquisition unit, 104b: Distributed representation acquisition unit, 105: Word selection unit Section 106: Similarity calculation section, 107: Score display section, 108: Text display section, 110: Input Unit, 120: Processing unit, 130: Storage unit, 140: Database, 150: Display unit, 160 : transmission line, 161a: communication unit, 161b: communication unit, 162: transmission line, 164: transmission line, 1 70: Memory unit, 180: Processing unit, 200: Reading comprehension support system, 210: Reading comprehension support system 220: Server, 230: Terminal

Claims

[Claim 1] The first step is to read the target document, The second step is to divide the read target document into multiple blocks, A third step involves obtaining word embeddings for each of the aforementioned multiple blocks, The fourth step is to read the query text, The fifth step involves extracting words contained in the aforementioned query text and obtaining word embeddings, A sixth step involves comparing the distributed representations of words between the words contained in the query statement and the words contained in each of the multiple blocks, determining the similarity, and calculating the score of the block. The seventh step is to present the blocks in order of the highest score, Includes, The first to third steps and the fourth to fifth steps can each be performed independently. In the sixth step, for each of the multiple blocks, a word matching a word in the query sentence is searched from among the words contained in the block, the similarity between the word embedding in the block and the word embedding in the query sentence is calculated for the matching word, and the score of the block is calculated. A reading comprehension support method in which, in the sixth step, if there are multiple matching words in the query text and the block, the sum of the similarity scores of the distributed representations for each word is used as the score for the block.

Images