JP2018045658A - Determination device and determination method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To allow for outputting information that assists creativity of a user.SOLUTION: A determination device disclosed herein comprises; an acquisition unit configured to acquire a random matrix, representing a distributed representation space of words belonging to a predetermined learning unit, for each learning unit; a computation unit configured to derive an eigenvalue of each random matrix acquired by the acquisition unit; and a determination unit configured to determine similarity among the learning units based on comparison of the eigenvalues derived by the computation unit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a determination device and a determination method.

  2. Description of the Related Art Conventionally, a technique for searching or generating information related to input information based on an analysis result of input information and outputting the searched or generated information as a response is known. As an example of such a technology, words, sentences, and contexts contained in the input text are converted into multidimensional vectors and analyzed, and based on the analysis result, text similar to the input text or input A natural language processing technique for analogizing text following text and outputting an analogy result is known.

JP 2006-127077 A

  However, in the above-described conventional technology, there are cases where information for assisting the creation of the user cannot be output.

  For example, in the above-described prior art, only information that can be predicted by the user, such as text similar to the input text or text following the input text, is output, and is related to the input text. However, it is difficult to output information that the user cannot predict. For this reason, the above-described conventional technology cannot provide information that gives inspiration to the user.

  The present application has been made in view of the above, and an object thereof is to enable output of information for assisting the creation of a user.

  The determination apparatus according to the present application calculates a random matrix indicating a distributed expression space of words belonging to a predetermined learning unit for each learning unit, and a calculation for calculating eigenvalues of the random matrix acquired by the acquisition unit. And a determination unit that determines similarity of the learning units based on a comparison result of the eigenvalues calculated by the calculation unit.

  According to one aspect of the embodiment, it is possible to output information that assists the creation of the user.

FIG. 1 is a diagram illustrating an example of a determination process executed by the determination apparatus according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the determination apparatus according to the embodiment. FIG. 3 is a diagram illustrating an example of information registered in the distributed representation space database according to the embodiment. FIG. 4 is a diagram illustrating an example of information registered in the determination result database according to the embodiment. FIG. 5 is a flowchart for explaining an example of the flow of determination processing according to the embodiment. FIG. 6 is a diagram illustrating an example of a hardware configuration.

  Hereinafter, modes for carrying out a determination device and a determination method according to the present application (hereinafter referred to as “embodiments”) will be described in detail with reference to the drawings. In addition, the determination apparatus and the determination method according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

[Embodiment]
[1-1. Example of determination device)
First, an example of processing executed by the determination apparatus will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a determination process executed by the determination apparatus according to the embodiment. In FIG. 1, the determination device 10 is an information processing device that executes a determination process described below, and is realized by, for example, a server device or a cloud system.

  More specifically, the determination device 10 is an arbitrary device such as the input device 100 or the information processing device 200 (for example, see FIG. 2) via a predetermined network N (for example, see FIG. 2) such as the Internet. Can communicate with.

  Here, the input apparatus 100 acquires a user's remarks using the audio | voice acquisition apparatus which acquires audio | voices, such as a microphone. Then, the input device 100 converts the speech into text data using an arbitrary voice recognition technique, and transmits the converted text data to the determination device 10. In addition, the information processing apparatus 200 reads out text data received from the determination apparatus 10 using a device that outputs sound, such as a speaker. The information processing apparatus 200 may display the text data received from the determination apparatus 10 on a predetermined display device.

  Note that the input device 100 and the information processing device 200 are realized by an information processing device such as a smart device such as a smartphone or a tablet, a desktop PC (Personal Computer), a notebook PC, or a server device. The input device 100 and the information processing device 200 may be realized by the same information processing device, for example, or may be realized by a device such as a robot.

[1-2. About the processing of the judgment device)
Here, in the prior art, text similar to the input text or text following the input text is inferred using a distributed expression represented by a multi-dimensional word vector constituting the input text. However, the prior art merely outputs text whose distributed representation is similar to the input text, that is, text that can be predicted by the user. For this reason, the conventional technology provides information that the user has never thought of, information that gives the user a new inspiration, that is, information that can cause the user's serendipity (inspiration, awareness, surprise). I could not. Also, for example, if text that does not resemble a simple input text is output, text that is not related to the user's thought will be output, which may hinder the user's thought. is there.

  On the other hand, when a user makes a statement having a predetermined conceptual structure that belongs to a certain field, it belongs to a field different from that field and has a conceptual structure possessed by the user's statement. When a sentence having a similar conceptual structure is output as a response, there is a possibility that a new inspiration can be given to the user. For example, when a user utters content belonging to the field of physics, the response includes a word group that belongs to the field of mathematics and has an analogy similar to the word group included in the user's speech If you do, there is a possibility that you can expand your ideas.

  Further, even if a response of content belonging to a field that is not similar to the field to which the user's remark belongs is output, it may be difficult for the user to understand, and the user's thinking may be hindered. However, if a response of content belonging to a field that is the same as or similar to the field to which the user's remark belongs is output, it may be possible to output only text that can be easily imagined by the user. .

  Therefore, the determination apparatus 10 determines the similarity between fields set with an arbitrary granularity by executing the following determination process. For example, the determination apparatus 10 acquires a random matrix indicating a distributed expression space of words belonging to a predetermined learning unit for each learning unit. Moreover, the determination apparatus 10 calculates each eigenvalue of the acquired random matrix. And the determination apparatus 10 determines the similarity of a learning unit based on the comparison result of the calculated eigenvalue.

  For example, the determination apparatus 10 acquires, as a predetermined learning unit, a random matrix indicating a distributed expression space of words belonging to a predetermined field for each field. And the determination apparatus 10 determines the similarity of each field | area based on the comparison result of the eigenvalue of the random matrix computed for every field | area.

  Here, the random matrix is a matrix in which matrix elements are assumed to be given according to a predetermined probability law or probability distribution. For example, the determination apparatus 10 converts various words into a distributed expression regardless of the field. For example, the determination apparatus 10 converts a word into a distributed expression using an arbitrary calculation method such as a w2v (word2vec) technique. In the following description, a distributed expression of a word may be described as a word vector.

Subsequently, the determination device 10 identifies a plurality of fields to be compared with an arbitrary granularity, and selects a distributed expression of words belonging to the field for each identified field. And the determination apparatus 10 produces | generates the random matrix A shown by the following formula | equation (1) from the dispersion | distribution expression of each word for every field. As a result, the determination apparatus 10 can express the distributed expression space of words belonging to one field by one random matrix. In Equation (1), vectors of n words belonging to a certain field are described as w _b1 to w _bn, and m predetermined probability distributions are described as w _a1 to w _am . Moreover, P shown in Formula (1) is a value shown as p in the following Formula (2), and is an expected value of the inner product of two word vectors. That is, the determination apparatus 10 sets a combination matrix of all words in a certain field as a random matrix having an expected value as an element.

  Here, when the distributed expression space of words belonging to one field is represented by a random matrix, it is considered that the characteristics of the random matrix correspond to the overall characteristics of the words belonging to the field. In addition, such overall characteristics for each field are considered to be an index for determining similarity between fields.

  Therefore, the determination apparatus 10 regards a random matrix generated from a distributed representation of words belonging to the same field as a random matrix indicating characteristics of the field (hereinafter, referred to as “random matrix of the field”). The similarity of each field is determined by comparing the features of the random matrix. More specifically, the determination apparatus 10 calculates eigenvalues of random matrices (that is, characteristics of random matrices) in each field using an arbitrary eigenvalue calculation technique such as a known eigenvalue calculation library. And the determination apparatus 10 compares the calculated eigenvalues, compares the characteristics of each field, and determines the similarity between fields based on the comparison result.

  For example, when the difference between the eigenvalues is larger than a predetermined threshold, the determination apparatus 10 determines that the similarity between the fields is lower than the predetermined threshold, and when the difference between the eigenvalues is equal to or less than the predetermined threshold, It is determined that the similarity between fields is equal to or greater than a predetermined threshold.

  As a result of such processing, the determination device 10 can determine the similarity between the fields based on the comparison result of the overall characteristics of the words belonging to each field. That is, the determination apparatus 10 can determine the similarity between fields based on the comparison result between the abstracted features of each field. As a result, the determination apparatus 10 selects, for example, another field whose abstract concept is similar to the field to which the sentence input by the user belongs, and is a sentence belonging to the selected field and input by the user. Since a sentence having a similar structure can be output, a sentence giving serendipity to the user can be output as a response.

[1-3. About learning units)
Here, the determination apparatus 10 may set a field to be compared with an arbitrary granularity. For example, when there is a field such as “internal medicine” or “surgery” in the field “medical field”, the determination device 10 generates an eigenvalue of a random matrix generated from a distributed representation of words belonging to the field “internal medicine” and the field “surgery”. The field “internal medicine” and the field “surgery” may be compared by comparing the eigenvalues of the random matrix generated from the distributed representation of the words belonging to “”. The determination apparatus 10 may compare, for example, the “medical field” including the field “internal medicine” and the field “surgery” and the “legal field” including the field “civil law” and the field “criminal law”. .

  Here, in the process of converting a word into a distributed representation such as w2v, there is a process of converting each word from a sentence or the like belonging to that field into a distributed representation for each predetermined field set in an arbitrary granularity. Has been done. Accordingly, the determination device 10 regards words belonging to a predetermined learning unit as words belonging to a predetermined field, such as a field set when each word is converted into a distributed expression, and uses the distributed expression of the word. The similarity between learning units may be determined by generating a random matrix and comparing eigenvalues of the random matrix.

[1-4. Use of eigenvectors)
Here, it is predicted that the characteristics of the random matrix appear not only in the eigenvalues but also in the eigenvectors. For example, the eigenvalue of a random matrix in a field indicates the general concept of words belonging to that field, and the eigenvector of such a random matrix is predicted to indicate the directivity of the general concept of words belonging to that field. The

  Therefore, the determination apparatus 10 may further calculate eigenvectors of the random matrix of each field, and determine the similarity between the fields based on the calculated eigenvalue comparison result and the eigenvector comparison result. For example, when the difference between the eigenvalues is equal to or smaller than a predetermined threshold and the value of the cosine similarity of the eigenvector is equal to or larger than the predetermined threshold (when the cosine similarity is equal to or larger than the predetermined threshold), the determination apparatus 10 You may determine with each field being similar.

[1-5. (Conversion between fields)
Here, a function (for example, a conversion function) for converting a random matrix in a certain field into a random matrix in another field can be obtained based on the eigenvalues of the random matrix. Such a function can be regarded as a function that changes the concept of words in the field corresponding to the random matrix before conversion into the concept of words in the field corresponding to the random matrix after conversion.

  Therefore, the determination apparatus 10 may generate a conversion function for converting a word belonging to the first learning unit into a word belonging to the second learning unit based on the calculated eigenvalue. And the determination apparatus 10 may produce | generate the response corresponding to the sentence which the user input using the produced | generated conversion function.

  For example, the determination apparatus 10 acquires sentences belonging to the first field from the user. In such a case, the determination apparatus 10 identifies the second field in which the similarity to the first field falls within a predetermined range based on the eigenvalues and eigenvectors of the random matrix in the first field. Subsequently, the determination apparatus 10 generates a conversion function for converting the random matrix of the first field into the random matrix of the second field. Note that the determination apparatus 10 does not need to generate a conversion function that completely converts a random matrix in the first field into a random matrix in the second field, and may generate a conversion function that converts with a predetermined accuracy. For example, the determination apparatus 10 may generate a conversion function that matches a predetermined proportion of the matrix elements of the random matrix in the first field with the matrix elements of the random matrix in the second field.

  And the determination apparatus 10 extracts a word from the sentence acquired from the user, and converts the extracted word into a distributed expression. Then, the determination apparatus 10 uses the conversion function to convert the extracted distributed representation of the word into a distributed representation of the word that can be regarded as belonging to the second field. Further, the determination device 10 generates a word belonging to the second field from a distributed representation of the word that can be regarded as belonging to the second field. For example, the determination apparatus 10 selects a word that is similar to the distributed representation of a word that can be regarded as the distributed representation belonging to the second field. And the determination apparatus 10 produces | generates a sentence using the selected word, and provides a produced sentence to a user as a response. As a result of such processing, the determination apparatus 10 can provide the user with a sentence that expands the range of ideas and causes serendipity.

[1-6. Example of processing executed by determination device]
Next, an example of determination processing executed by the determination device 10 will be described with reference to FIG. First, the determination apparatus 10 converts a distributed representation of words belonging to different fields into a random matrix (step S1). For example, the determination apparatus 10 calculates a distributed representation of each of the words # 1-1 to # 1-4 belonging to the field # 1, and uses the equation (1) from the calculated distributed representation to calculate the total of the field # 1. A random matrix # 1 showing a typical feature is generated. In addition, for example, the determination apparatus 10 calculates a distributed representation of each of the words # 2-1 to # 2-4 belonging to the field # 2, and uses the equation (1) from the calculated distributed expression to calculate the field # 2. Generate a random matrix # 2 indicating the overall characteristics of.

  Subsequently, the determination apparatus 10 calculates eigenvalues and eigenvectors of each random matrix (step S2). For example, the determination apparatus 10 calculates the eigenvalue # 1 and the eigenvector # 1 from the random matrix # 1, and calculates the eigenvalue # 2 and the eigenvector # 2 from the random matrix # 2.

  Then, the determination device 10 determines the similarity of each field based on the comparison result of the eigenvalues and the comparison result of the eigenvectors (step S3). For example, when the difference between the eigenvalue # 1 and the eigenvalue # 2 is equal to or less than a predetermined threshold and the value of the cosine similarity between the eigenvector # 1 and the eigenvector # 2 is equal to or greater than the predetermined threshold, It is determined that the field # 1 and the field # 2 are similar fields. Note that the determination device 10 may determine that the field # 1 and the field # 2 are similar when the difference between the unique value # 1 and the unique value # 2 is equal to or smaller than a predetermined threshold. In addition, the determination apparatus 10 comprehensively considers the value of the difference between the eigenvalue # 1 and the eigenvalue # 2 and the value of the cosine similarity between the eigenvector # 1 and the eigenvector # 2 to determine the field # 1 and the field #. It may be determined whether 2 is similar. For example, the determination apparatus 10 employs a threshold that dynamically varies according to the difference between the eigenvalue # 1 and the eigenvalue # 2, the value of the cosine similarity between the eigenvector # 1 and the eigenvector # 2, and the like. Also good. Moreover, the determination apparatus 10 may set an arbitrary threshold according to the degree of similarity desired by the user.

  Here, it is assumed that the determination device 10 has acquired a user's remarks (step S4). In such a case, the determination apparatus 10 converts a word included in the input utterance sentence into a word in a similar field, and generates a sentence having the same structure as the input sentence (step S5). For example, the determination apparatus 10 extracts a word from a sentence of an input utterance using a technique such as morphological analysis. And the determination apparatus 10 specifies the field | area to which a user's utterance belongs from the extracted word.

  Subsequently, the determination device 10 selects a field similar to the specified field, and includes the input speech sentence using a conversion function that converts a random matrix of the specified field into a random matrix of the selected field. Convert the words to be used to the selected field. For example, in the case where the sentence of the input speech belongs to the field # 1 and the field # 2 exists as a field similar to the field # 1, the determination apparatus 10 changes the random matrix of the field # 1 to the random matrix of the field # 2. Using the conversion function for converting to, the words extracted from the text of the input utterance are converted to the words in the field # 2.

  More specifically, the determination apparatus 10 converts the distributed expression of words extracted from the input sentence sentence using a conversion function. Further, the determination device 10 selects a distributed expression similar to the distributed expression converted using the conversion function from among the distributed expressions of the words belonging to the field # 2, and specifies the word corresponding to the selected distributed expression. Then, the determination apparatus 10 generates a sentence that belongs to the field # 2 using the selected word and has a structure similar to the input sentence (that is, a sentence having a similar relationship between words). The generated sentence is output (step S6). As a result, for example, the determination apparatus 10 can cause the information processing apparatus 200 to speak the generated sentence as a response.

[2. (Configuration of judgment device)
Hereinafter, an example of a functional configuration of the determination apparatus 10 that realizes the above-described determination process will be described. FIG. 2 is a diagram illustrating a configuration example of the determination apparatus according to the embodiment. As illustrated in FIG. 2, the determination device 10 includes a communication unit 20, a storage unit 30, and a control unit 40.

  The communication unit 20 is realized by, for example, a NIC (Network Interface Card). The communication unit 20 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from the input device 100 and the information processing device 200.

  The storage unit 30 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 30 also stores a distributed representation space database 31 and a determination result database 32.

  In the distributed expression space database 31, words converted into distributed expressions are registered for each field. For example, FIG. 3 is a diagram illustrating an example of information registered in the distributed representation space database according to the embodiment. As illustrated in FIG. 3, information having items such as “field”, “word”, and “distributed expression” is registered in the distributed expression space database 31.

  Here, the “field” is an identifier indicating the field to which the word indicated by the associated “word” belongs. The “word” is a word corresponding to the distributed expression, that is, a text. The “distributed expression” is a distributed expression of the associated “word”. In the example shown in FIG. 3, conceptual values such as “word # 1-1” and “distributed expression # 1-1” are described. However, in actuality, text data indicating various words and distributed expressions are used. A certain multidimensional quantity or the like is registered.

  For example, in the example shown in FIG. 3, the field “field # 1”, the word “word # 1-1”, and the distributed expression “distributed expression # 1-1” are registered in the distributed expression space database 31 in association with each other. ing. Such information indicates that “word # 1-1” is a word belonging to “field # 1” and its distributed expression is “distributed expression # 1-1”.

  Returning to FIG. 2, the description will be continued. In the determination result database 32, similarity relationships in each field are registered as determination results by the above-described determination processing. For example, FIG. 4 is a diagram illustrating an example of information registered in the determination result database according to the embodiment. As shown in FIG. 4, information having items such as “first field”, “second field”, and “conversion function” is registered in the determination result database 32. Here, “first field” and “second field” indicate fields having a similar relationship, and “conversion function” indicates information indicating a conversion function for converting a random matrix in a field having an associated similar relationship. It is.

  For example, in the example illustrated in FIG. 4, the first field “field # 1”, the second field “field # 2”, and the conversion function “conversion function # 1” are registered in association with each other. Such information is determined that “field # 1” and “field # 2” are similar, and a conversion function for converting a random matrix of “field # 1” into a random matrix of “field # 2” is “ This indicates that the function is “conversion function # 1”.

  Returning to FIG. 2, the description will be continued. The control unit 40 is a controller. For example, various programs stored in a storage device inside the determination apparatus 10 are stored in a RAM or the like by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). This is realized by being executed as a work area. The control unit 40 is a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  As illustrated in FIG. 2, the control unit 40 includes an acquisition unit 41, a calculation unit 42, a determination unit 43, a generation unit 44, and an output unit 45.

  The acquisition unit 41 acquires a random matrix indicating a distributed expression space of words belonging to a predetermined learning unit for each learning unit. For example, the acquisition unit 41 acquires, as a predetermined learning unit, a random matrix indicating a distributed expression space of words belonging to a predetermined field for each field. As a more specific example, the acquisition unit 41 refers to the distributed expression space database 31 and selects a distributed expression of a word associated with a predetermined field. And the acquisition part 41 produces | generates the random matrix of a predetermined field | area by Formula (1) mentioned above using the selected dispersion | distribution expression. In addition, the acquisition unit 41 repeats such processing for each field, thereby generating random matrices for all fields.

  The calculation unit 42 calculates eigenvalues of the random matrix. In addition, the calculation unit 42 further calculates an eigenvector of the random matrix. For example, the calculation unit 42 calculates eigenvalues and eigenvectors from the random matrix generated for each field by the acquisition unit 41.

  The determination unit 43 determines the similarity of learning units based on the comparison result of the eigenvalues. For example, the determination unit 43 determines the similarity of each field based on the comparison result of the eigenvalues. Note that the determination unit 43 may determine the similarity of learning units based on the comparison result of eigenvalues and the comparison result of eigenvectors. For example, the determination unit 43 may determine the similarity of learning units based on the comparison result of eigenvalues and the value of cosine similarity between eigenvectors.

  As a more specific example, the determination unit 43 acquires eigenvalues and eigenvectors calculated by the calculation unit 42 for each field. Then, the determination unit 43 compares eigenvalues and eigenvectors for all combinations of fields, and determines whether or not each field is similar based on the comparison result. For example, the determination unit 43 determines that the difference between the eigenvalue of the field # 1 and the eigenvalue of the field # 2 is equal to or less than a predetermined threshold, and the value of the cosine similarity between the eigenvector of the field # 1 and the eigenvector of the field # 2 Is equal to or greater than a predetermined threshold value, it is determined that field # 1 and field # 2 are similar. Then, the determination unit 43 registers field # 1 and field # 2 in association with the determination result database 32.

  The generation unit 44 generates a conversion function for converting a word belonging to the first learning unit to a word belonging to the second learning unit based on the eigenvalue. For example, the generation unit 44 refers to the determination result database 32 and identifies the field # 1 and the field # 2 that are determined to be similar by the determination unit 43. In such a case, the generation unit 44 calculates a conversion function # 1 that converts the random matrix of the field # 1 into the random matrix of the field # 2 from the eigenvalue of the field # 1 and the eigenvalue of the field # 2. Then, the generation unit 44 registers the calculated conversion function # 1 in the determination result database 32 in association with the field # 1 and the field # 2. Note that the generation unit 44 may calculate the conversion function using the eigenvector.

  Further, the generation unit 44 generates a sentence belonging to the second learning unit as a response to the sentence input by the user from the sentence belonging to the first learning unit input by the user using the conversion function. To do. For example, when the generation unit 44 receives a sentence of a user's statement from the input device 100, the generation unit 44 extracts a word from the sentence and specifies a field to which the extracted word belongs using the distributed expression space database 31 or the like. Subsequently, the generation unit 44 refers to the determination result database 32 and selects, from the determination result database 32, a conversion function for converting a random matrix in the identified field into a random matrix in a field similar to that field.

  And the production | generation part 44 converts the word extracted from the sentence of a user's utterance into the word of a similar field | area using the conversion function selected from the determination result database 32. FIG. Thereafter, the generation unit 44 uses the converted word to generate a sentence having the same structure as the sentence input by the user.

  The output unit 45 outputs the text generated by the generation unit 44 as a response to the text input by the user. For example, the output unit 45 outputs the text generated by the generation unit 44 to the information processing apparatus 200 and instructs to output the output text as a response to the utterance received from the input device 100. As a result, the information processing apparatus 200 can output a response.

[3. Example of flow of processing executed by determination device]
Next, an example of a flow of determination processing executed by the determination device 10 will be described with reference to FIG. FIG. 5 is a flowchart for explaining an example of the flow of determination processing according to the embodiment. First, the determination apparatus 10 extracts word groups belonging to each field (step S101), and obtains a random matrix indicating a distributed expression space including a distributed expression of word groups belonging to the same field (step S102). That is, the determination apparatus 10 acquires a random matrix for each field. Then, the determination device 10 calculates eigenvalues and eigenvectors of the acquired random matrix (step S103), determines similarity between fields based on a comparison result between the calculated eigenvalues and eigenvectors (step S104), The process ends.

[4. (Modification)
In the above, an example of the determination process by the determination apparatus 10 has been described. However, the embodiment is not limited to this. Hereinafter, the variation of the determination process which the determination apparatus 10 performs is demonstrated.

[4-1. Use of judgment results)
For example, the determination apparatus 10 may execute processing for determining model similarity using the determination processing described above. For example, the determination apparatus 10 generates a first random matrix from a group of distributed expressions generated from a certain word group using the first model, and generates a distributed expression generated from the same word group using the second model. A second random matrix is generated from the group. And the determination apparatus 10 may determine the similarity of a 1st model and a 2nd model based on the comparison result of the eigenvalue of a 1st random matrix, and the eigenvalue of a 2nd random matrix. When such processing is executed, for example, the determination apparatus 10 can determine whether or not the second model can be used instead of the first model.

[4-2. Device configuration〕
In the example described above, the determination device 10 executes the determination process in the determination device 10. However, the embodiment is not limited to this. For example, the determination apparatus 10 receives from a user using a back-end server that determines similarity between fields based on a comparison result of eigenvalues and eigenvectors of a random matrix, and a similarity determination result and a conversion function. You may implement | achieve by the front end server which converts a sentence and outputs it as a response. Further, the determination apparatus 10 may store the distributed representation space database 31 and the determination result database 32 in an external storage server.

[4-3. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, information including various data and parameters shown in the above text and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the above-described embodiments can be appropriately combined within a range in which processing contents are not contradictory.

[5. program〕
Further, the determination apparatus 10 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 6, for example. FIG. 6 is a diagram illustrating an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090. Have

  The arithmetic device 1030 operates based on a program stored in the primary storage device 1040 and the secondary storage device 1050, a program read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic device 1030 for various arithmetic operations. The secondary storage device 1050 is a storage device in which data used for various calculations by the calculation device 1030 and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD, a flash memory, or the like.

  The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information such as a monitor and a printer. For example, USB (Universal Serial Bus), DVI (Digital Visual Interface), This is realized by a standard connector such as HDMI (registered trademark) (High Definition Multimedia Interface). The input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, a USB.

  The input device 1020 includes, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), and a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), and a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. The input device 1020 may be an external storage medium such as a USB memory.

  The network IF 1080 receives data from other devices via the network N and sends the data to the arithmetic device 1030, and transmits data generated by the arithmetic device 1030 to other devices via the network N.

  The arithmetic device 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic device 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040, and executes the loaded program.

  For example, when the computer 1000 functions as the determination device 10, the arithmetic device 1030 of the computer 1000 implements the function of the control unit 40 by executing a program loaded on the primary storage device 1040.

[6. effect〕
As described above, the determination apparatus 10 acquires a random matrix indicating a distributed expression space of words belonging to a predetermined learning unit for each learning unit. Moreover, the determination apparatus 10 calculates each eigenvalue of the acquired random matrix. And the determination apparatus 10 determines the similarity of a learning unit based on the comparison result of the calculated eigenvalue. As a result, for example, the determination apparatus 10 can identify a field having a similar relative concept, so that the sentence is similar in structure to the sentence input by the user, and is the sentence input by the user. You can output texts from different fields. As a result, the determination apparatus 10 can output information that assists the creation of the user.

  Further, the determination apparatus 10 acquires, as a predetermined learning unit, a random matrix indicating a distributed expression space of words belonging to a predetermined field for each field. And the determination apparatus 10 determines the similarity of a field | area based on the comparison result of an eigenvalue. As a result, the determination apparatus 10 can determine the similarity of fields based on the comparison result of the overall concept of each field.

  The determination device 10 further calculates eigenvectors of the random matrix, and determines the similarity of the learning units based on the comparison result of the eigenvalues and the comparison result of the eigenvectors. For example, the determination apparatus 10 determines the similarity of learning units based on the comparison result of eigenvalues and the value of cosine similarity between eigenvectors. As a result, the determination apparatus 10 can improve the accuracy of determining the similarity in the field.

  Further, the determination apparatus 10 generates a conversion function for converting a word belonging to the first learning unit to a word belonging to the second learning unit based on the calculated eigenvalue. Further, the determination device 10 generates a sentence belonging to the second learning unit as a response to the sentence input by the user from the sentence belonging to the first learning unit input by the user using the conversion function. To do. For this reason, the determination apparatus 10 is a sentence that the user has not imagined from the sentences input by the user, and the sentence input by the user in a field different from the field to which the sentence input by the user belongs. A sentence having a similar context can be output. As a result, the determination apparatus 10 can output information that assists the creation of the user.

  As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and various modifications, including the aspects described in the disclosure section of the invention, based on the knowledge of those skilled in the art, It is possible to implement the present invention in other forms with improvements.

  Moreover, the above-mentioned “section (module, unit)” can be read as “means”, “circuit”, and the like. For example, the generation unit can be read as generation means or a generation circuit.

DESCRIPTION OF SYMBOLS 10 Determination apparatus 20 Communication part 30 Storage part 31 Distributed expression spatial data database 32 Determination result database 40 Control part 41 Acquisition part 42 Calculation part 43 Determination part 44 Generation part 45 Output part 100 Input apparatus 200 Information processing apparatus

Claims (7)

An acquisition unit that acquires, for each learning unit, a random matrix indicating a distributed expression space of words belonging to a predetermined learning unit;
A calculation unit for calculating each eigenvalue of the random matrix acquired by the acquisition unit;
And a determination unit that determines similarity of the learning units based on a comparison result of the eigenvalues calculated by the calculation unit. The acquisition unit acquires, as the predetermined learning unit, a random matrix indicating a distributed expression space of words belonging to a predetermined field for each field,
The determination apparatus according to claim 1, wherein the determination unit determines similarity in the field based on a comparison result of the eigenvalues. The calculation unit further calculates an eigenvector of the random matrix,
The determination apparatus according to claim 1, wherein the determination unit determines similarity of the learning units based on the comparison result of the eigenvalues and the comparison result of the eigenvectors. The determination apparatus according to claim 3, wherein the determination unit determines similarity of the learning units based on a comparison result of the eigenvalues and a value of cosine similarity between the eigenvectors. The generator further includes: a generation unit that generates a conversion function for converting a word belonging to the first learning unit to a word belonging to the second learning unit based on the eigenvalue calculated by the calculation unit. The determination apparatus according to any one of? The generation unit generates a sentence belonging to the second learning unit as a response to the sentence input by the user from the sentence belonging to the first learning unit input by the user, using the conversion function. The determination apparatus according to claim 5. A determination method executed by a determination device,
An acquisition step of acquiring, for each learning unit, a random matrix indicating a distributed expression space of words belonging to a predetermined learning unit;
A calculation step of calculating each eigenvalue of the random matrix acquired by the acquisition step;
And a determination step of determining similarity of the learning units based on a comparison result of the eigenvalues calculated by the calculation step.

Images