Nippon Telegraph and Telephone Corporation

Ntt Corporation

Kyosuke Nishida

Junji Tomita

Hisako Asano

Itsumi Saito

Atsushi Otsuka

Kosuke Nishida

Ryuichiro Higashinaka

Taichi Katayama

Nozomi Kobayashi

Ryo Ishii

Yasuhito Osugi

Katsuji Bessho

Narichika Nomoto

Yoshihiro Matsuo

Taku Hasegawa

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.

Learning apparatus, information processing apparatus, learning method, information processing method and program

A text generation apparatus includes a memory and a processor configured to, based on learned parameters of neural networks, acquire, as a reference text, a predetermined number of two or more sentences having a relatively high relevance to an input sentence from a set of sentences different from the input sentence and generate text based on the input sentence and the reference text, such that information to be considered when generating text can be added as text.

Text generation apparatus, text generation learning apparatus, text generation method, text generation learning method and program

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.

A dialogue processing apparatus includes one or more computers each including a memory and a processor configured to receive a question Qas a word string representing a current question in an interactive machine reading comprehension task, a question history {Q, . . . , Q} as a set of word strings representing previous questions, and an answer history {A, . . . , A} 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 Ato the question Qand 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.

Dialogue processing apparatus, learning apparatus, dialogue processing method, learning method and program

A nonverbal information generation apparatus includes a nonverbal information generation unit that generates time-information-stamped nonverbal information that corresponds to time-information-stamped text feature quantities on the basis of the time-information-stamped text feature quantities and a learned nonverbal information generation model. The time-information-stamped text feature quantities are configured to include feature quantities that have been extracted from text and time information representing times assigned to predetermined units of the text. The nonverbal information is information for controlling an expression unit that expresses behavior that corresponds to the text.

Nonverbal information generation apparatus, nonverbal information generation model learning apparatus, methods, and programs

An encoding unit transforms a piece of text divided into a plurality of spans that are subdivided units of the piece of text and a question which have been input into a vector representation sequence representing a meaning of a span and the question based on the piece of text and the question which have been input using a pre-trained encoding model for transforming input text into a vector representation sequence representing a meaning of the input text. For each of the spans, an evidence extraction unit estimates an evidence score indicating the degree to which the span is suitable as the evidence for extracting the answer using a pre-trained extraction model for calculating the evidence score based on the vector representation sequence.

Answer generating device, answer learning device, answer generating method, and answer generating program

A sentence generation device has: an estimation unit for receiving input of a first sentence and an output length, and estimating importance of each word constituting the first sentence using a pre-trained model; and a generation unit for generating a second sentence based on the importance, and thus makes it possible to evaluate importance of a constituent element of an input sentence, in correspondence with a designated output length.

Text generation apparatus, text generation method, text generation learning apparatus, text generation learning method and program

A sentence generation device has: an estimation unit for receiving input of a first sentence and a focus point related to generation of a second sentence to be generated based on the first sentence, and estimating importance of each word constituting the first sentence using a pre-trained model; and a generation unit for generating the second sentence based on the importance, and thus makes it possible to evaluate importance of a constituent element of an input sentence in correspondence with a designated focus point.

Sentence generation using pre-trained model with word importance and focus point

A nonverbal information generation apparatus includes a display unit that partitions text into predetermined units, displays the text partitioned into the predetermined units, and makes nonverbal information that represents information about behavior of a verbal output agent or nonverbal information that represents information about behavior of a receiver of verbal information of the verbal output agent that corresponds to the text when the verbal output agent outputs the verbal information visible in association with the predetermined units of the text.

Nonverbal information generation apparatus, method, and program

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 unitselects pieces of external knowledge based on similarity degrees between pieces of external knowledge included in an external knowledge databaseand the input sentence Q, using a neural network, and causes the selected pieces of external knowledge to be search results R. A processing unitacquires 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 unitcalculates 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. A learning unitupdates neural network parameters of the second external knowledge search unitusing the consideration v.

Learning device, learning method and learning program

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.

Learning apparatus, search apparatus, learning method, search method and program

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

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.

Question responding apparatus, question responding method and program

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.

Growing community of inventors

Tokyo, Japan

Kyosuke Nishida