National Institute of Information and Communications Technology, Incorporated

Jonghoon Oh

Kentaro Torisawa

Chikara Hashimoto

Ryu Iida

Canasai Kruengkrai

Julien Kloetzer

Stijn De Saeger

Kiyonori Ootake

Noriyuki Abe

Yutaka Kidawara

Junichi Kazama

Motoki Sano

Masahiro Tanaka

Takao Kawai

Kanako Onishi

Takuya Kawada

Junta Mizuno

Yoshihiko Asao

Istvan Varga

Yiou Wang

Kazuma Kadowaki

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 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 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 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.

Dialogue system and computer program therefor

[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 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

An annotation data generation assisting system includes: an input/output device receiving an input through an interactive process; morphological analysis systemand dependency parsing system performing morphological and dependency parsing on text data in text archive; first to fourth candidate generating units detecting a zero anaphor or a referring expression in the dependency relation of a predicate in a sequence of morphemes, identifying a position as an object of annotation and estimating candidates of expressions to be inserted by using language knowledge; a candidate DB storing estimated candidates; and an interactive annotation device reading candidates of annotation from candidate DB and annotate a candidate selected by an interactive process by input/output device.

Annotation assisting apparatus and computer program therefor

In order to provide a non-factoid question answering system with improved precision, the question answering system () includes: a candidate retrieving unit (), responsive to a question, extracting answer candidates from a corpus storage (); a feature vector generating unit () for generating features from combinations of a question with each of the answer candidates; SVMs () trained to calculate a score of how correct a combination of the question with an answer candidate is, upon receiving the feature vector therefor; and an answer ranker unit () outputting the answer candidate with the highest calculated score as the answer. The features are generated on the basis of the results of morphological analysis and parsing of the question, a phrase in the question evaluated as being positive or negative as well as its polarity, and the semantic classes of nouns in the features.

Non-factoid question-answering system and computer program

A predicate template collector allowing efficient and automatic recognition of predicate templates is adapted to include: a noun pair collectorand a noun pair polarity determinerfor collecting noun pairs co-occurring with predicate template pairs and determining polarity of relation between nouns, using conjunctions and seed templates; a template pair collector, collecting template pairs co-occurring with noun pairs and determining, based on the relation of noun pairs co-occurring with the predicate template pairs and the conjunctions between predicate templates pairs, whether the polarity of excitatory class of predicate template pair is the same or not; a template network builderbuilding a template network connecting predicate templates based on the predicate template pairs and match/mismatch of excitatory class thereof; and a template excitation value calculatorcalculating excitation value to be assigned to each node, using the excitation value of seed templates and the relation between each of the nodes in the network.

Growing community of inventors

Tokyo, Japan

Jonghoon Oh