Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/04—Architecture, e.g. interconnection topology
  • G06N3/0475—Generative networks
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N5/00—Computing arrangements using knowledge-based models
  • G06N5/02—Knowledge representation; Symbolic representation

Definitions

• This disclosure relates to a learning device, a learning method, and a learning program.
• Knowledge graphs are a means of describing real-world knowledge in a form that is easy for computers to read. Knowledge expressed in knowledge graphs can be applied to a variety of purposes, including search systems and dialogue systems. A specific example is the use of knowledge graphs in product recommendation systems for customers.
• Patent Literature 1 discloses a technique for embedding entity-relationships in a vector space by searching an external database to identify relations that are inversely equivalent to each other, and increasing the number of entity-relationship combinations based on the identified relations.
• this technique has a problem in that when auxiliary information such as text is attached to the entity-relationships, the auxiliary information cannot be used to learn the embedded representation.
• the present disclosure aims to improve the expressiveness of knowledge graph embedding by utilizing text information corresponding to entities and relations.
• the learning device includes: When each element of a triplet consisting of two entities and one relation included in a target knowledge graph, which is a knowledge graph, is taken as a target element, the embedding learning unit generates an embedding vector corresponding to the target element based on a target vector expression corresponding to the target element and text information corresponding to the target element, and learns a knowledge graph embedded expression corresponding to the target knowledge graph based on the generated embedding vector.
• an embedding learning unit when each element of a triplet is a target element, an embedding learning unit generates an embedding vector corresponding to the target element based on a target vector representation corresponding to the target element and text information corresponding to the target element, and learns a knowledge graph embedding representation based on the generated embedding vector.
• a triplet consists of two entities and one relation included in the target knowledge graph. Therefore, according to the present disclosure, by utilizing text information corresponding to entities and relations, the expressive power of knowledge graph embedding can be improved.
• FIG. 1 is a diagram showing an example of the configuration of an information processing system 90 according to a first embodiment.
• FIG. 1 is a diagram showing an example of the configuration of a learning device 100 according to a first embodiment.
• FIG. 10 is a diagram showing a specific example of a triplet D1 according to the first embodiment.
• FIG. 10 is a diagram showing a specific example of a triplet D1 according to the first embodiment.
• FIG. 1 is a diagram showing an example of the hardware configuration of a learning device 100 according to a first embodiment. 4 is a flowchart showing the operation of the learning device 100 according to the first embodiment.
• FIG. 10 is a diagram showing an example of the hardware configuration of a learning device 100 according to a modification of the first embodiment.
• FIG. 10 is a diagram showing an example of the configuration of an information processing system 91 according to a second embodiment.
• FIG. 10 is a diagram showing an example of the configuration of a learning device 101 according to a second embodiment.
• 10 is a flowchart showing the operation of the learning device 101 according to the second embodiment.
• FIG. 10 is a diagram showing an example of the configuration of an information processing system 92 according to a third embodiment.
• FIG. 10 is a diagram showing an example of the configuration of a learning device 102 according to a third embodiment.
• 10A and 10B are diagrams illustrating the processing of the acquisition unit 160 according to the third embodiment, in which FIG. 10A illustrates the processing of generating a query D9, and FIG. 10B illustrates the processing of generating a prompt D10.
• 10 is a flowchart showing the operation of the learning device 102 according to the third embodiment.
• the information processing system 90 includes a learning device 100, a triplet DB 200, a document DB 300, and a language model 400.
• DB is an abbreviation for database.
• the information processing system 90 has a function of learning knowledge graph embedding representations.
• the information processing system 90 may be used for knowledge graph completion tasks such as link prediction, such as finding the author of a paper from the body of the paper.
• the information processing system 90 learns a knowledge graph embedded representation using triples each consisting of an entity and a relation in the knowledge graph. When learning the knowledge graph embedded representation, if there is text corresponding to an element in the triple, that text is used.
• the knowledge graph learned by the information processing system 90 is used, for example, in a product or service recommendation system, a search system, a dialogue system, a question-answering system, or a decision support system.
• FIG. 2 shows an example of the configuration of the learning device 100 according to the first embodiment.
• the learning device 100 includes a data receiving unit 110 , an acquiring unit 120 , a training unit 130 , and a storage unit 140 .
• the data receiving unit 110 has the function of receiving a triplet D1 from the triplet DB 200, acquiring any element contained in the received triplet D1 as an element D2, and acquiring a vector representation D3 of the acquired element D2.
• the triple D1 is data that indicates a combination of a head h and a tail t, which correspond to two entities included in the knowledge graph, and one relation r corresponding to the two entities.
• the triple D1 consists of two entities and one relation included in the target knowledge graph, which is a knowledge graph.
• the triple D1 is usually expressed in the format ⁇ h, r, t>.
• Element D2 is an element selected from the elements included in triplet D1, i.e., element D2 represents one of h, r, and t. A specific example of the triplet D1 and element D2 will be described with reference to FIGS.
• FIG. 3 shows an example of each triplet D1 received by the data receiving unit 110.
• each triple D1 consists of a head h, a tail t, and a relation r.
• label strings representing each element of the head h, tail t, and relation r are stored.
• the triple ⁇ Bob, is_born_on, 14 July 1990> represents the fact that "Bob was born on July 14, 1990.”
• the data receiving unit 110 selects an arbitrary element from the triplet D1 and stores the selected element in element D2.
• the value stored in element D2 is either "Bob", "is_born_on", or "14 July 1990".
• FIG. 4 shows another example of the triplet D1 received by the data receiving unit 110.
• the values stored in the head h, tail t, and relation r included in the triplet D1 are not necessarily label strings representing each element.
• each element may be converted into a format that is easy to handle within a computer, such as an ID, such as E0001.
• the data receiving unit 110 receives, as triplet D1, each ID representing the triplet, along with a correspondence table between IDs and labels.
• the data receiving unit 110 uses the input correspondence table to associate each ID with a label, thereby restoring each element of the triplet to a label string.
• the vector expression D3 acquired by the data receiving unit 110 is a structural vector expression, and corresponds to the vector expression corresponding to the element D2.
• the vector expression D3 is expressed as a real-valued vector of any dimension that represents the element D2.
• the data receiving unit 110 inquires of the storage unit 140 whether a vector expression corresponding to element D2 exists. If a vector expression corresponding to element D2 exists, the data receiving unit 110 designates the existing vector expression as vector expression D3. On the other hand, if a vector expression corresponding to element D2 does not exist, the data receiving unit 110 generates a real-valued vector using an arbitrary initialization method and designates the generated real-valued vector as vector expression D3.
• the data receiving unit 110 may generate the real-valued vector using random numbers that follow a uniform distribution, or may use a normal distribution instead of the uniform distribution.
• the initialization method is not an essential feature of the present disclosure.
• the data receiving unit 110 outputs the element D2 to the obtaining unit 120 and outputs the vector representation D3 to the training unit 130.
• the acquisition unit 120 has a function of acquiring text D4 corresponding to element D2 input from the data receiving unit 110 from the document DB 300.
• the acquisition unit 120 may also have a function of determining whether text information corresponding to element D2 exists in the document DB 300.
• the document DB 300 is a database made up of document data.
• Text D4 corresponding to element D2 corresponds to text information corresponding to element D2, and specifically, is text that explains element D2 or text that is supplementary information to element D2. As a specific example, if element D2 is "The Mona Lisa" shown in FIG. 3, text D4 corresponding to element D2 is text that explains what kind of painting the Mona Lisa is. Note that text D4 corresponding to element D2 does not necessarily exist in document DB 300. Text D4 corresponding to element D2 may also be text accompanying element D2.
• the acquisition unit 120 includes an information acquisition unit 121 .
• the information acquisition unit 121 acquires text D4 corresponding to the target element from the document DB 300.
• the target element is each element D2 of the triplet D1.
• the information acquisition unit 121 acquires text D4 corresponding to element D2 input from the data receiving unit 110 from the document DB 300.
• a value indicating that no text exists is stored in text D4 instead of the text.
• the stored value may be a special character such as Null. However, the stored value is not an essential feature of the present disclosure.
• the information acquisition unit 121 outputs the acquired text D4 to the feature extraction unit 131.
• the training unit 130 has the function of creating an embedded vector D6 corresponding to element D2 by combining the vector representation D3 output by the data receiving unit 110 with a text vector D5 obtained by vectorizing the text D4 output by the information acquisition unit 121.
• the training unit 130 includes a feature extraction unit 131 and an embedded learning unit 132 .
• the feature extraction unit 131 generates a target text vector corresponding to the text D4 acquired by the information acquisition unit 121 based on the target language model.
• the target text vector corresponds to the text vector D5.
• the target language model corresponds to the language model 400.
• the feature extraction unit 131 has a function of vectorizing the text D4 output by the information acquisition unit 121 based on the language model 400, thereby extracting a text vector D5.
• the language model 400 may be a model using a classical model such as Bag of Words or Term Frequency-Inverse Document Frequency (TF-IDF), or may be a model using a deep neural network such as Bidirectional Encoder Representations from Transformers (BERT).
• TF-IDF Term Frequency-Inverse Document Frequency
• the text D4 output by the information acquisition unit 121 may contain a special value indicating that no text exists. If a special value is contained in the text D4, the feature extraction unit 131 does not perform vectorization processing using the language model 400, and stores the special value indicating that no text vector exists in the text vector D5.
• the stored value may be a special character such as Null. However, the stored value is not an essential feature of the present disclosure.
• the feature extraction unit 131 outputs the text vector D5 to the embedding learning unit 132.
• the embedding learning unit 132 generates an embedding vector D6 corresponding to the target element based on a target vector representation corresponding to the target element and text information corresponding to the target element, and learns a knowledge graph embedded representation corresponding to the target knowledge graph based on the generated embedding vector D6. Specifically, the embedding learning unit 132 generates an embedding vector D6 based on the target vector representation and the target text vector. The target vector representation corresponds to the vector representation D3. If text information corresponding to the target element does not exist in the document DB 300, the embedding learning unit 132 sets the target vector representation as the embedding vector D6.
• the embedding learning unit 132 may match the number of dimensions between the target vector representation and the target text vector, and generate the embedding vector D6 by combining the target vector representation and the target text vector after matching the number of dimensions.
• the embedding learning unit 132 has the function of taking as input the vector representation D3 output by the data receiving unit 110 and the text vector D5 output by the feature extraction unit 131, and learning an embedding vector D6 corresponding to element D2.
• the processing of the embedded learning unit 132 differs depending on whether or not a special value indicating that the text vector does not exist is stored in the text vector D5.
• the embedding learning unit 132 uses the obtained embedding vector D6 to calculate a score using any known knowledge graph embedding learning algorithm.
• the embedding learning unit 132 calculates the score using [Equation 1].
• Each of h, r, and t on the right side of [Equation 1] is a vector representation obtained by the embedded learning unit 132.
• the embedding learning unit 132 calculates the error, gradient, etc. using an arbitrary knowledge graph embedding learning algorithm.
• the calculated error, gradient, score, and vector representation are each stored in the memory unit 140.
• Memory 12 is typically a volatile storage device, a specific example of which is RAM (Random Access Memory). Memory 12 is also called primary storage device or main memory. Data stored in memory 12 is saved in secondary storage device 13 as needed.
• RAM Random Access Memory
• Each part of the learning device 100 may use the input/output IF 14 and communication device 15 as appropriate when communicating with other devices.
• the learning program may be recorded on a computer-readable non-volatile recording medium.
• Specific examples of non-volatile recording media include optical disks and flash memory.
• the learning program may be provided as a program product.
• Step S1 The data receiving unit 110 acquires the triplet D1 from the triplet DB 200 as learning data.
• Step S2 The data receiving unit 110 acquires any element (h, r, or t) included in the acquired triplet D1 as element D2.
• Step S7 The information acquisition unit 121 determines whether text corresponding to element D2 is stored in text D4. If the information acquisition unit 121 determines that text corresponding to element D2 is stored in text D4, the process proceeds to step S8, and if the information acquisition unit 121 determines that text corresponding to element D2 is not stored in text D4, the process proceeds to step S11.
• Step S8 The feature extraction unit 131 obtains a text vector D5 by vectorizing the text stored in the text D4 using the language model 400.
• Step S9 The embedded learning unit 132 adjusts either the number of dimensions of the vector representation D3 corresponding to the element D2 or the number of dimensions of the text vector D5 corresponding to the element D2, thereby aligning the number of dimensions of the vector representation D3 with the number of dimensions of the text vector D5.
• Step S10 The embedding learning unit 132 generates a final embedding vector D6 corresponding to the element D2 by combining the vector representation D3 corresponding to the element D2 with the text vector D5 corresponding to the element D2.
• Step S11 The embedding learning unit 132 uses the vector representation D3 corresponding to the element D2 as the final embedding vector D6 corresponding to the element D2.
• Step S12 The embedded learning unit 132 determines whether or not an unprocessed element exists. If the embedded learning unit 132 determines that an unprocessed element exists, the process returns to step S2. If the embedded learning unit 132 determines that an unprocessed element does not exist, the process proceeds to step S13.
• the embedding learning unit 132 updates the parameters of the knowledge graph embedding model by performing processes such as error calculation and gradient calculation using the vector representation obtained for each of the elements (h, r, and t) of the triplet D1.
• Step S14 The embedding learning unit 132 determines whether or not there are any unprocessed triplet(s). If the embedding learning unit 132 determines that there are any unprocessed triplet(s), the process returns to step S1. If the embedding learning unit 132 determines that there are no unprocessed triplet(s), the process proceeds to step S15.
• Step S15 The storage unit 140 stores the updated model and parameters.
• the learning device 100 learns an embedding representation by combining the structural information of the entity relations with the corresponding text information when generating a vector representation of any element included in a triplet. Therefore, according to this embodiment, the expressive power of knowledge graph embedding can be improved, and the performance of key tasks for knowledge graph completion, such as link prediction and entity alignment, can be improved.
• the learning device 100 when generating a vector representation of any element included in a triplet, if there is no text explaining each element, the learning device 100 according to embodiment 1 learns using only the structural vector representation of each element. Therefore, according to this embodiment, it is possible to improve the accuracy of link prediction, entity alignment, and the like, even in knowledge graphs in which auxiliary text information does not correspond to all elements.
• FIG. 7 shows an example of the hardware configuration of the learning device 100 according to this modification.
• the learning device 100 includes a processing circuit 18 instead of the processor 11 , the processor 11 and memory 12 , the processor 11 and auxiliary storage device 13 , or the processor 11 , memory 12 and auxiliary storage device 13 .
• the processing circuitry 18 is hardware that realizes at least some of the components of the learning device 100 .
• Processing circuitry 18 may be dedicated hardware or may be a processor that executes programs stored in memory 12 .
• processing circuitry 18 When processing circuitry 18 is dedicated hardware, processing circuitry 18 may be, for example, a single circuit, multiple circuits, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof.
• the learning device 100 may include a plurality of processing circuits that replace the processing circuit 18. The plurality of processing circuits share the role of the processing circuit 18.
• the learning device 100 some functions may be realized by dedicated hardware, and the remaining functions may be realized by software or firmware.
• Processing circuitry 18 is illustratively implemented in hardware, software, firmware, or a combination thereof.
• the processor 11, memory 12, auxiliary storage device 13, and processing circuit 18 are collectively referred to as the “processing circuitry.”
• the functions of each functional component of the learning device 100 are realized by the processing circuitry.
• Learning devices according to other embodiments may also have the same configuration as this modified example.
• Embodiment 2 The following mainly describes the differences from the above-described embodiment with reference to the drawings.
• the document DB 300 is removed from the configuration of the first embodiment, and a character string generating unit 152 is added to the configuration of the first embodiment, which performs normalization processing on character strings directly assigned to any element included in a triplet.
• the learning device 101 acquires a label directly assigned to any element included in a triplet, normalizes the acquired label, and vectorizes the normalized label using a language model. This process makes it possible to utilize the label information representing the entity-relation contained in the label, improve the expressive power of knowledge graph embedding, and improve link prediction accuracy, even when the total amount of text corresponding to a certain element is extremely small.
• FIG. 8 shows an example of the configuration of an information processing system 91 according to the second embodiment.
• the configuration of the information processing system 91 is the same as the configuration of the information processing system 90 according to the first embodiment, except that the information processing system 91 does not have the document DB 300 according to the first embodiment.
• FIG. 9 shows an example of the configuration of a learning device 101 according to the second embodiment.
• the learning device 101 includes a data receiving unit 110 , an acquiring unit 150 , a training unit 130 , and a storage unit 140 .
• the data receiving unit 110, the training unit 130, and the storage unit 140 are the same as those in the first embodiment.
• the acquisition unit 150 has the function of acquiring a label string D7 that is directly assigned to an element D2 input from the data receiving unit 110, generating a normalized label string D8 by performing a string normalization process on the acquired label string D7, and outputting the generated normalized label string D8.
• the acquisition unit 150 includes an information acquisition unit 151 and a character string generation unit 152 .
• the information acquisition unit 151 acquires the label character string D7 that is directly assigned to the element D2 input from the data receiving unit 110.
• a character string representing element D2 is stored in element D2 input from data receiving unit 110. That is, if the triplet input to data receiving unit 110 is ⁇ Tokyo, is_capital_of, Japan> and the element "Tokyo" is selected, the character string stored in element D2 is "Tokyo.” Therefore, the actual function of information acquiring unit 151 is simply to assign the value of element D2 to label character string D7.
• the character string generating unit 152 performs normalization processing on the target label character string to generate a normalized label character string D8.
• the normalized label character string D8 corresponds to text information corresponding to the target element.
• the target label character string corresponds to the label character string D7.
• the string generation unit 152 generates a normalized label string D8 by performing a string normalization process on the label string D7 input from the information acquisition unit 151, and outputs the generated normalized label string D8 to the feature extraction unit 131.
• the string generation unit 152 performs deletion of underscores included in the label string D7 and deletion of frequently occurring words such as "is” and "of."
• the string stored in the label string D7 is "is_capital_of”
• the string stored in the normalized label string D8 becomes "is capital of” by deleting the underscores, and becomes "capital” by deleting the frequently occurring words.
• this example is merely an example of the normalization process.
• the specific method of the string normalization process is not an essential feature of the present disclosure.
• the character string generating unit 152 may not necessarily perform character string normalization processing, and may simply use the value of the label character string D7 as the normalized label character string D8.
• the feature extraction unit 131 generates a target text vector corresponding to the normalized label string D8 generated by the string generation unit 152, based on the target language model.
• Step S6a The information acquisition unit 151 acquires the label character string directly assigned to the element D2 input from the data receiving unit 110, and stores the acquired label character string in the label character string D7.
• Step S6b The string generation unit 152 generates a normalized label string by performing a string normalization process on the label string D7 input from the information acquisition unit 151, and stores the generated normalized label string in a normalized label string D8.
• the learning device 101 according to the second embodiment substitutes the label of an element for the text corresponding to the element. Therefore, according to the second embodiment, even for a knowledge graph that has no elements linked to the document DB 300 or a knowledge graph that has extremely few elements linked to the document DB 300, the accuracy of downstream tasks such as link prediction and entity alignment can be improved.
• Embodiment 3 The following mainly describes the differences from the above-described embodiment with reference to the drawings.
• a character string generating unit 162, a searching unit 163, and an explanatory model 500 are added to the configuration of the first embodiment.
• the label for each element is often "Tokyo" or "capital.”
• the information obtained from such labels is limited.
• the explanatory model 500 include a Neural Network (NN) model, a Convolutional Neural Network (CNN) model, a Recurrent Neural Network (RNN), a Variational Autoencoder (VAE), Generative Adversarial Networks (GAN), a Diffusion model, a Transformer model, a Large Language Model (LLM), a Visual Language Model (VLM), a BERT, and a Generative Pre-trained Model (GPT).
• the explanatory model 500 may be a model called a Language Transformer (CLIP) or a Contrastive Language-Image Pre-training (CLIP).
• CLIP Language Transformer
• CLIP Contrastive Language-Image Pre-training
• the explanatory model 500 may also be a rule-based model that obtains output results by referencing a predetermined table or making a decision based on predetermined conditions.
• the above-mentioned models are not necessarily exclusive.
• the LLM, VLM, BERT, and GPT are each included in the Transformer model.
• the Transformer model is included in the NN model.
• each of the learning algorithms and models may be a combination of multiple types.
• the models also include what is called a multimodal model, which is learned by combining multiple different types of data.
• FIG. 12 shows an example of the configuration of a learning device 102 according to the third embodiment.
• the learning device 102 includes a data receiving unit 110 , an acquiring unit 160 , a training unit 130 , and a storage unit 140 .
• the data receiving unit 110, the training unit 130, and the storage unit 140 are the same as those in the first embodiment.
• the acquisition unit 160 has the function of acquiring a label string D7 directly assigned to an element D2 input from the data receiving unit 110, creating a query D9 for searching for text related to the acquired label string D7, or a prompt D10 for outputting text that explains the acquired label string, searching for or generating text using the created query D9 or prompt D10, and outputting the obtained text D11.
• the acquisition unit 160 includes an information acquisition unit 161 , a character string generation unit 162 , and a search unit 163 .
• the information acquisition unit 161 is the same as in the second embodiment.
• the string generation unit 162 generates a query D9 used to search the document DB 300 for text D11 corresponding to the target label string included in the target element.
• the string generation unit 162 generates a prompt D10 used to cause the explanation model 500 to generate text D11 corresponding to the target label string included in the target element.
• the query D9 is used to search for text D11 related to the input label string D7.
• the prompt D10 is used to cause the explanation model 500 to generate text D11 that explains the input label string D7.
• the string generation unit 162 when the label string D7 is input from the information acquisition unit 161, the string generation unit 162 generates a query D9 or a prompt D10.
• FIG. 13 is a conceptual diagram showing a specific example of the processing of the character string generating unit 162.
• a specific example of processing when the character string generating unit 162 generates a query D9 will be described, and then a specific example of processing when the character string generating unit 162 generates a prompt D10 will be described.
• label string D7 corresponding to element D2 is input to string generation unit 162 from information acquisition unit 161.
• String generation unit 162 generates query D9 for searching for text including input label string D7.
• the generated query D9 is queried by search unit 163 to document DB 300.
• 13A is an example of a query D9 when a GET request is sent to a Hypertext Transfer Protocol (HTTP) server to search for text containing the character string "tokyo" when the document DB 300 is implemented by the HTTP server.
• HTTP Hypertext Transfer Protocol
• the format of the query D9 generated by the character string generation unit 162 corresponds to the format of the document DB 300.
• the label string D7 corresponding to the element D2 is input to the string generation unit 162 from the information acquisition unit 161.
• the string generation unit 162 generates the prompt D10 to generate text that explains the label string D7.
• the generated prompt D10 is queried by the explanation model 500 via the search unit 163.
• 13(b) is an example of a prompt D10 when inputting a prompt to the generative language model to generate text that explains the character string "tokyo" when the explanatory model 500 is a generative language model configured using GPT or the like.
• the format and wording of the prompt D10 generated by the character string generation unit 162 are in accordance with the form of the explanatory model 500.
• the search unit 163 acquires text information corresponding to the target element by searching the document DB 300 based on the query D9 generated by the character string generation unit 162.
• the search unit 163 inputs the prompt D10 generated by the character string generation unit 162 into the explanation model 500 to acquire text information corresponding to the target element.
• the search unit 163 inputs the query D9 or prompt D10 input from the string generation unit 162 into the document DB 300 or the explanatory model 500, and outputs the obtained response to the feature extraction unit 131 as text D11 corresponding to the element D2.
• the search unit 163 inputs a query D9 to the document DB 300.
• a specific example of processing will be described in which the search unit 163 inputs a prompt D10 to the explanatory model 500.
• the search unit 163 inputs the query D9 generated by the character string generation unit 162 to the document DB 300.
• the document DB 300 outputs one of the texts containing the label character string D7 based on the query D9.
• the output text is stored in text D11, which is then input to the feature extraction unit 131.
• the search unit 163 inputs the prompt D10 generated by the character string generation unit 162 to the explanation model 500.
• the explanation model 500 outputs text that explains the label character string D7 based on the prompt D10.
• the output text is stored in text D11, which is then input to the feature extraction unit 131.
• the feature extraction unit 131 generates a target text vector corresponding to the text D11 acquired by the search unit 163 based on the target language model.
• ***Explanation of Operation*** 14 is a flowchart showing an example of the operation of the learning device 102.
• the operation of the learning device 102 will be described with reference to FIG.
• steps S6c and S6d are executed, unlike the process shown in Fig. 10. Therefore, steps S6c and S6d will be described with reference to Fig. 14.
• the other steps shown in Fig. 14 are assigned the same step numbers as those shown in Fig. 10, and descriptions of the processes will be omitted.
• Step S6c The string generator 162 generates a query D9 that searches for text related to the label string D7, or a prompt D10 that generates text that explains the label string D7.
• Step S6d The search unit 163 inputs the query D9 input from the character string generation unit 162 into the document DB 300, or inputs the prompt D10 input from the character string generation unit 162 into the explanatory model 500. Thereafter, the search unit 163 stores the obtained text in the text D11.
• the learning device 102 acquires text describing an element from an external resource by searching the document DB 300 for text related to the label string of the element, as the text corresponding to the element. Therefore, according to this embodiment, the accuracy of downstream tasks such as link prediction and entity alignment can be improved.
• the learning device 102 generates text for the explanatory model 500 that explains the label string of an element as text corresponding to the element. Therefore, according to this embodiment, text that explains elements can be flexibly used even in knowledge graphs that have no elements linked to the document DB 300 or in knowledge graphs with extremely few elements linked to the document DB 300. Furthermore, according to this embodiment, the accuracy of downstream tasks such as link prediction and entity alignment can be improved.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• Physics & Mathematics (AREA)
• Data Mining & Analysis (AREA)
• General Engineering & Computer Science (AREA)
• Software Systems (AREA)
• Mathematical Physics (AREA)
• Computational Linguistics (AREA)
• General Physics & Mathematics (AREA)
• Evolutionary Computation (AREA)
• Artificial Intelligence (AREA)
• Computing Systems (AREA)
• Molecular Biology (AREA)
• General Health & Medical Sciences (AREA)
• Life Sciences & Earth Sciences (AREA)
• Biophysics (AREA)
• Biomedical Technology (AREA)
• Health & Medical Sciences (AREA)
• Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Priority Applications (2)

Applications Claiming Priority (1)

Publications (1)

Family

ID=93797743

Family Applications (1)

Country Status (2)

Families Citing this family (1)

Citations (2)

• 2024
  • 2024-02-16 JP JP2024530440A patent/JP7599622B1/ja active Active
  • 2024-02-16 WO PCT/JP2024/005618 patent/WO2025173264A1/ja active Pending

Patent Citations (2)

Non-Patent Citations (1)

Also Published As

Similar Documents

Legal Events