National Institute of Information and Communications Technology, Incorporated

Kentaro Torisawa

Chikara Hashimoto

Jonghoon Oh

Yutaka Kidawara

Ryu Iida

Stijn De Saeger

Canasai Kruengkrai

Julien Kloetzer

Motoki Sano

Noriyuki Abe

Junichi Kazama

Kiyonori Ootake

Yulan Yan

Takuya Kawada

Kanako Onishi

Masaki Murata

Yoshihiko Asao

Kow Kuroda

Junta Mizuno

Jun Goto

Masahiro Tanaka

Takao Kawai

Istvan Varga

Yiou Wang

Masaaki Tsuchida

Kazuma Kadowaki

Kazuaki Inada

A program for training a representation generator generating a representation representing an answer part included in a passage to classify whether the passage is related to an answer or not. The program causes a computer to operate as: a fake representation generator responsive to a question and a passage for outputting a fake representation representing an answer part of the passage; a real representation generator for outputting, for the question and a core answer, a real representation representing the core answer, in the same format as fake representation; a discriminator for discriminating whether fake representation and real representation are a real or fake representation; and a generative adversarial network unit training the discriminator and fake representation generator through generative adversarial network such that error determination of fake representation is maximized and error determination of real representation is minimized.

Answer classifier and representation generator for question-answering system using GAN, and computer program for training the representation generator

A request paraphrasing systemallowing a dialogue system to flexibly address to requests in various different manners of expression includes: a pre-processing unitconverting a user inputto a word vector sequence; and a neural paraphrasing modeltrained in advance by machine learning to receive the word vector sequence as an input and paraphrasing a request represented by the word vector sequence to a request having a higher probability of obtaining an answer from a question-answering devicethan the request before paraphrasing. As pre-processing, whether the user inputis a request or not may be determined and it may be paraphrased only when it is determined to be a request. Further, a classification modelmay classify the input request to determine to which request class it belongs, and the classification may be input as one feature to neural paraphrasing model

Request paraphrasing system, request paraphrasing model and request determining model training method, and dialogue system

A causality recognizing apparatus includes a candidate vector generating unit configured to receive a causality candidate for generating a candidate vector representing a word sequence forming the candidate; a context vector generating unit generating a context vector representing a context in which noun-phrases of cause and effect parts of the causality candidate appear; a binary pattern vector generating unit, an answer vector generating unit and a related passage vector generating unit, generating a word vector representing background knowledge for determining whether or not there is causality between the noun-phrase included in the cause part and the noun-phrase included in the effect part; and a multicolumn convolutional neural network learned in advance to receive these word vectors and to determine whether or not the causality candidate has causality.

Causality recognizing apparatus and computer program therefor

A question answering device includes: a general word vector converter converting a question and an answer to semantic vectors in accordance with general context; a general sentence level CNN, in response to similarities of semantic vectors between words in question and answer and to strength of causality between the words, for weighting each semantic vector to calculate sentence level representations of the question and the answer; a general passage level CNN, in response to similarity between sentence level representations of question and answer, and to strength of relation of vectors in the sentence level representations viewed from causality, for weighting the sentence level representation to calculate a passage level representation for the question and answer passage; and a classifier determining whether or not an answer is a correct answer, based on the similarities between outputs from CNNsand

Non-factoid question-answering device

A dialogue system includes a response utterance selecting unit generating a response utterance original sentence to an input utterance; an input utterance emotion estimating unit estimating emotion of the input utterance by calculating input utterance emotion scores indicating degree of matching between the emotion represented by the input utterance and a plurality of emotions; and a response utterance modifying unit for calculating response utterance emotion scores of a response utterance original sentence as emotion scores for each of the plurality of emotions, modifying the response utterance original sentence by a method of modification determined by the values of input utterance emotion score and the response utterance emotion score, and thereby generating and outputting a response utterance.

Dialogue system and computer program therefor

A summary generating apparatus includes a text storage device storing text with information indicating a portion to be focused on; word vector converters vectorizing each word of the text and adding an element indicating whether the word is focused on or not to the vector and thereby converting the text to a word vector sequence; an LSTM implemented by a neural network performing sequence-to-sequence type conversion, pre-trained by machine learning to output, in response to each of the word vectors of the word vector sequence input in a prescribed order, a summary of the text consisting of the words represented by the word sequence; and input units inputting each of the word vectors of the word vector sequence in the prescribed order to the neural network.

Summary generating apparatus, summary generating method and computer program

A scenario passage pair recognizer includes: a text passage searching unit searching a set of text passages each including no more than a certain number of sentences of a document, and within which all noun phrases included in a scenario candidate co-occur; a feature extracting unit extracting a feature from each combination of the scenario candidate and each searched support passage; a classifier outputting a score indicating reliability of the scenario candidate based on the support passage as a source of the feature; and a score accumulating unit and a maximum value selecting unit, accumulating the scores output from the classifier and selecting the maximum value as the reliability of the scenario candidate. The scenario classifier determines plausibility of the scenario candidate as a causality based on the feature including the score output from the scenario passage pair recognizer.

Scenario passage pair recognizer, scenario classifier, and computer program therefor

A dialogue system includes: a question generating unit receiving an input sentence from a user and generating a question using an expression included in the input sentence, by using a dependency relation; an answer obtaining unit inputting the question generated by the question generating unit to a question-answering system and obtaining an answer to the question from question-answering system; and an utterance generating unit for generating an output sentence to the input sentence, based on the answer obtained by the answer obtaining unit.

[Object] To provide a system for automatically and reliably collecting information belonging to a given category, and matching the information appropriately in a timely manner. [Solution] A text classifying deviceanalyzes dependency of collected texts by a morpheme analyzing unitand a dependency analyzing unit. A problem report collecting unitspecifies a core consisting of noun+predicate in a text based on dependency relation of the text, and using a combination of noun classification (trouble/non-trouble) and predicate classification (excitatory/inhibitory), classifies the text to a problem report or the rest, by a method referred to as core-based matrix. Support information collecting deviceand request message collecting devicecollect support information and request messages in the similar manner. A matching devicematches problem reports and support information collected by problem report collecting unitand support information collecting deviceby a method referred to as co-occurrence core matrix, and thus associates problem information (support information) with appropriate support information (problem information).

Text matching device and method, and text classification device and method

A credibility determining system enabling highly accurate credibility determination of given information includes causal relation knowledge DBand search scope constraint DB. Causal relation knowledge each includes a combination of cause and result parts, and time and position constraints associated with the causal relation. The credibility determining system further includes a query generating unitretrieving a causal relation matching the input information and based on the time and position constraints stored in search scope constraint DBin association with the retrieved causal relation, generating a query for retrieving remarks from mini-blog text DB, a text search unitsearching for related remarks from mini-blog text DBusing the query, and a display candidate selecting unitclassifying the searched remarks to expressions interpreted as causes or to results, determining credibility of the input information based on the classification result and outputting the determination result.

System and method for determining credibility of information based on many remarks on a network, and non-transitory computer readable storage medium having stored thereon computer program therefor

A question-answering system capable of appropriately answering a non-factoid question. The question-answering system responsive to a question, for taking out answer candidates from an object document storage unit; extracting plausible ones from the answer candidates; recognizing causal relation expression included in extracted answer candidates; determining whether or not a recognized causal relation is relevant as an answer; generating a feature vector related to a combination of the question and the searched answer candidate; and for calculating, when a feature vector is given, a score indicating a degree of how correct an answer candidate is as an answer to the question, for the question and the answer candidate as a source of the feature vector, and for outputting, as the answer to the question, an answer candidate having the highest score.

Non-factoid question-answering system and method

[Object] An object of the present invention is to provide a system for collecting elements as a basis for generating a social scenario useful for people to make well-balanced good decision. [Solution] A scenario generating apparatus includes: a causality phrase pair DBstoring causality phrase pairs; synonimity generatorsand, searching, for each of the causality phrase pairs, causality phrase pairs having a cause phrase with causal consistency with the result phrase of the causality phrase pair, and generating join information for joining causality phrase pairs; join relation DBstoring the join information; and a causality joining unitjoining, to a result phrase of a causality phrase pair, a causality phrase pair having a cause phrase with causal consistency with the phrase by using the join information, and thereby linking causality. A join relation generatorthat finds a hidden relation between phrases and linking causality phrase pairs may be provided.

Scenario generating apparatus and computer program therefor

A system for collecting elements as a basis for generating a social scenario useful to make a well-balanced good decision. A complex predicate template collecting apparatus includes: a simple predicate template DB storing simple predicate templates having positive or negative polarity values added; an object noun dictionary; a complex predicate template candidate extractor extracting complex predicate template candidates each formed of a combination of a word specified by the object noun dictionary and a simple predicate template, from a WEB archive; a sahen-noun polarity adder, a quantifier noun polarity adder and a trouble-noun polarity adder, determining polarity of a noun in each of the complex predicate template candidate; and a complex predicate template polarity calculator calculating polarity of a complex predicate template candidate by a combination of the polarity of the noun and the polarity of the simple predicate template included in the complex predicate template.

Complex predicate template collecting apparatus and computer program therefor

An entailment pattern pair extension apparatusextends entailment pairs by generating an n-term entailment pair from an m-term entailment pair, where m and n are integers not smaller than 0 and satisfying m&#x3c;n. Each entailment pair includes a first language pattern and a second language pattern entailed by the first language pattern. Entailment pattern pair extension apparatusincludes: a generation rule storage unitstoring generation rules for generating n-term entailment pairs from m-term entailment pairs, and a binary pair adding unitreceiving m-term entailment pair, determining, for each generation rule stored in the generation rule storage unit, whether its condition is satisfied by the m-term pair, and if the condition is satisfied, applying a modification rule of the generation rule to each language pattern constituting the m-term entailment pair.

Entailment pair extension apparatus, computer program therefor and question-answering system

[Object] To provide a device assisting a user to easily generate, in relation to an issue of interest to the user, a question sentence guaranteed to have an answer of a certain accuracy or higher in a question-answering system. [Solution] A question sentence generating device is used with a question-answering system, and it includes: word receiving means for receiving a wordas a source for generating a question sentence; and question sentence generating databasecomprised of a plurality of entries for generating a question sentence. Each of the plurality of entries has a word as a key and includes an answer sentence pattern co-occurring with the word, used in the question-answering system. The question sentence generating device further includes a question sentence generating unit, searching the question sentence generating databasefor an answer sentence pattern using the wordreceived by the word receiving means as a key, for generating a question sentence from a retrieved answer sentence pattern and the received word

Growing community of inventors

Tokyo, Japan

Kentaro Torisawa