Abstract: There is provided a learning device for learning a neural network used for search of external knowledge in order to increase search accuracy of external knowledge required for arithmetic processing. With an input sentence Q as an input, an external knowledge search unit 22 selects pieces of external knowledge based on similarity degrees between pieces of external knowledge included in an external knowledge database 2 and the input sentence Q, using a neural network, and causes the selected pieces of external knowledge to be search results R2. A processing unit 14 acquires a response sentence A to the input sentence Q by arithmetic processing with the input sentence Q and the selected pieces of external knowledge as an input. A consideration calculation unit 23 calculates a consideration v determined from an index indicating correctness of the response sentence A based on a true output T given to the input sentence Q in advance and an index indicating quality of the selected pieces of external knowledge.

Abstract: A structured text processing learning apparatus includes a memory, and a processor configured to: analyze a structure of structured text, extract, from the structured text, information related to a predetermined structure to be extracted based on the structure, generate a converted document including text data in which each string indicating a structure of the extracted information has been converted, in accordance with the structure related to the extracted information, and train a neural network for executing predetermined processing for the converted document, using, as input, the generated converted document and correct answer information for performing the predetermined processing. Thus, application of a neural network to structured text is facilitated.

Abstract: A generation unit that takes a question Qi that is a word sequence representing a current question in a dialogue, a document P used to generate an answer Ai to the question Qi, a question history {Qi-1, . . . , Qi-k} that is a set of word sequences representing k past questions, and an answer history {Ai-1, . . . , Ai-k} that is a set of word sequences representing answers to the k questions as inputs, and generates the answer Ai by machine reading comprehension in an extractive mode or a generative mode using pre-trained model parameters is provided.

Abstract: A learning apparatus according to an embodiment has a feature generation means configured to take a search query, a first document related to the search query, and a second document that is not related to the search query as input, and generate a feature of the search query, a feature of the first document, and a feature of the second document, by using model parameters of a neural network, and an update means configured to take the feature of the search query, the feature of the first document, and the feature of the second document as input, and update the model parameters by using an error function including a cost function that is a differentiable approximation function of an L0 norm.

Abstract: A generation unit that takes a question Qi that is a word sequence representing a current question in a dialogue, a document P used to generate an answer Ai to the question Qi, a question history {Qi-1, . . . , Qi-k} that is a set of word sequences representing k past questions, and an answer history {Ai-1, . . . , Ai-k} that is a set of word sequences representing answers to the k questions as inputs, and generates the answer Ai by machine reading comprehension in an extractive mode or a generative mode using pre-trained model parameters is provided.

Abstract: A learning apparatus executes receiving a text and a question associated with the text, and calculating an evidence score expressing a likelihood of a character string included in the text as evidence for an answer to the question by using a model parameter of a first neural network; extracting, by sampling from a predetermined distribution having the evidence score as a parameter, a first set indicating a set of the character strings as the evidence for the answer from the text; receiving the question and the first set and extracting the answer from the first set by using a model parameter of a second neural network; and learning the model parameters of the first and second neural networks by calculating a gradient through error back propagation by using a continuous relaxation and a first loss between the answer and a true answer to the question.

Abstract: A text generation apparatus includes a content selection unit that acquires a reference text based on an input text and information different from the input text and a generation unit that generates a text based on the input text and the reference text, wherein the content selection unit and the generation unit are neural networks based on learned parameters, so that information to be considered when generating a text can be added as text.

Abstract: A question generation device includes: generating means which uses a query and a relevant document including an answer to the query as input and, using a machine learning model having been learned in advance, generates a revised query in which a potentially defective portion of the query is supplemented with a word included in a prescribed lexical set.

Abstract: A text generation apparatus includes a memory and a processor configured to execute acquiring a reference text based on an input text and information different from the input text; and generating a text based on the input text and the reference text, wherein the acquiring and the generating are implemented as neural networks based on learned parameters.

Abstract: To make it possible to accurately generate a word vector even if vocabulary of a word vector data set is not limited. In a vector generating device 10 that generates vectors representing an input sentence P, when generating a series of the vectors representing the input sentence P based on vectors corresponding to words included in the input sentence P, a definition-sentence-considered-context encode unit 280 generates, based on a dictionary DB 230 storing sets of headwords y and definition sentences Dy, which are sentences defining the headwords y, concerning a word, which is the headword stored in the dictionary DB, among the words included in the input sentence P, the series of the vectors representing the input sentence P using the definition sentence Dy of the headwords y.

Abstract: A language processing apparatus includes: a preprocessing unit that splits an input text into a plurality of short texts; a language processing unit that calculates a first feature and a second feature using a trained model for each of the plurality of short texts; and an external storage unit configured to store a third feature for one or more short texts, and the language processing unit uses the trained model to calculate the second feature for a certain short text using the first feature of the short text and the third feature stored in the external storage unit.

Abstract: An appropriate vector of any phrase can be generated. A lattice construction unit 212 constructs a lattice structure formed by links binding adjacent word or phrase candidates based on a morphological analysis result and a dependency analysis result of input text. A first learning unit 213 performs learning of a neural network A for estimating nearby word or phrase candidates from word or phrase candidates based on the lattice structure. A vector generation unit 214 acquires a vector of each of the word or phrase candidates from the neural network A and sets the vector as learning data. A second learning unit performs learning of a neural network B for vectorizing the word or phrase candidates based on the learning data.

Abstract: This disclosure is provided, in which an answer generation unit configured to receive a document and a question as inputs, and execute processing of generating an answer sentence for the question by a learned model by using a word included in a union of a predetermined first vocabulary and a second vocabulary composed of words included in the document and the question, in which the learned model includes a learned neural network that has been learned in advance whether word included in the answer sentence is included in the second vocabulary, and increases or decreases a probability at which a word included in the second vocabulary is selected as the word included in the answer sentence at the time of generating the answer sentence by the learned neural network.

Abstract: A learning device of a phrase generation model includes a memory; and a processor configured to execute learning the phrase generation model including an encoder and a decoder, by using, as training data, a 3-tuple. The 3-tuple includes a combination of phrases and at least one of a conjunctive expression representing a relationship between the phrases, and a relational label indicating the relationship represented by the conjunctive expression. The encoder is configured to convert a phrase into a vector from a 2-tuple. The 2-tuple includes a phrase and at least one of the conjunctive expression and the relational label. The decoder is configured to generate, from the converted vector and the conjunctive expression or the relational label, a phrase having the relationship represented by the conjunctive expression or the relational label with respect to the phrase.

Abstract: A text generation apparatus includes a processor and a memory storing program instructions that cause the processor to receive an input sentence including one or more words and generate a sentence: estimate an importance of each word included in the input sentence and encode the input sentence; and take the importance and a result of encoding the input sentence as inputs to generate the sentence based on the input sentence. The processor uses a neural network based on learned parameters. This improves the accuracy of sentence generation.

Abstract: A learning apparatus according to an embodiment has a feature generation means configured to take a search query, a first document related to the search query, and a second document that is not related to the search query as input, and generate a feature of the search query, a feature of the first document, and a feature of the second document, by using model parameters of a neural network, and an update means configured to take the feature of the search query, the feature of the first document, and the feature of the second document as input, and update the model parameters by using an error function including a cost function that is a differentiable approximation function of an L0 norm.

Abstract: To enable provision of appropriate information for a user query even in a case there are multiple information provision modules which are different in answer generation processing. A query sending unit 212 sends a user query to each one of a plurality of information provision module units 220 that are different in the answer generation processing and that each generate an answer candidate for the user query. An output control unit 214 performs control such that the answer candidate acquired from each one of the plurality of information provision module units 220 is displayed on a display unit 300 on a per-agent basis with information on an agent associated with that information provision module unit 220.

Abstract: A dialogue processing apparatus includes one or more computers each including a memory and a processor configured to receive a question Qi as a word string representing a current question in an interactive machine reading comprehension task, a question history {Qi, . . . , Qi?1} as a set of word strings representing previous questions, and an answer history {A1, . . . , Ai?1} as a set of word strings representing previous answers to the previous questions, and use a pre-learned first model parameter, to generate an encoded context vector reflecting an attribute or an importance degree of each of the previous questions and the previous answers; and receive a document P to be used to generate an answer Ai to the question Qi and the encoded context vector, and use a pre-learned second model parameter, to perform matching between the document and the previous questions and previous answers, to generate the answer.

Abstract: The present disclosure relates to concurrent learning of a relationship estimation model and a phrase generation model. The relationship estimation model estimates a relationship between phrases. The phrase generation model generates a phrase that relates to an input phrase. The phrase generation model includes an encoder and a decoder. The encoder converts a phrase into a vector using a three-piece set as learning data. The decoder generates, based on the converted vector and a connection expression or a relationship label, a phrase having a relationship expressed by the connection expression or the relationship label for the phrase. The relationship estimation model generates a relationship score from the converted vector, which indicates each phrase included in a combination of the phrases, and a vector indicating the connection expression and the relationship label.

Abstract: In a training data generation method, a computer executes: a generation step for generating partial data of a summary sentence created for text data; an extraction step for extracting, from the text data, a sentence set that is a portion of the text data, based on a similarity with the partial data; and a determination step for determining whether or not the partial data is to be used as training data for a neural network that generates a summary sentence, based on the similarity between the partial data and the sentence set. Thus, it is possible to streamline the collection of training data for a neural summarization model.