Nec Corporation

Pioneer Corporation

Pioneer Electronic Corporation

Sony Corporation

Elpida Memory, Inc.

Nippon Telegraph and Telephone Corporation

Teijin Limited

Panasonic Corporation

Tohoku University

Kyoto University

Honda Motor Co., Ltd.

Honda Giken Kogyo Kabushiki Kaisha

Massachusetts Institute of Technology

Kabushiki Kaisha Toshiba

Alps Alpine Co., Ltd.

Jun Suzuki

Yoshihiro Yamaguchi

Kenji Suzuki

Toru Takahashi

Yuki Hayashi

Youichi Hidaka

Masaki Kan

Junichi Higuchi

Takashi Yoshikawa

Katsumi Ishii

Atsushi Iwata

Hirokazu Iizuka

Kunihiro Takei

Takanori Maeda

Hideyuki Shimonishi

Satoshi Sugiura

Yataro Ichikawa

Kiyoshi Tateishi

Kiyoshi Kobayashi

Yasuji Koshikawa

Hiromasa Noda

Atsushi Onoe

Akira Tsuji

Shigekazu Nagata

Yasuhiro Matsumoto

Toshihiko Kurihara

Tsutomu Nakamura

Kenji Yoneda

Chiaki Dono

Yuichiro Ishii

Yoshiro Riho

Satoshi Yamamoto

Masahiko Takahashi

Masato Yasuda

Tetsuya Kohno

Masaaki Suzuki

Kiyoshi Sato

Hideki Gochou

Nobuyuki Enomoto

Shuichi Kubouchi

Toshihiko Watanabe

Yasuyoshi Watanabe

Nobutaka Nakajima

Nobuharu Kami

Katsuya Kikuiri

Shigeyuki Yanagimachi

Kunihiko Kinugasa

Takuya Araki

Ken Suzuki

Tsuyoshi Hagiwara

Eiji Kuroki

Kazutaka Goami

Sho Takase

Masaaki Nagata

Yorimasa Suwa

Takayuki Yamazawa

Tsukio Masegi

Kazuo Kitai

Teruyuki Baba

Satoshi Nakamura

Takami Arai

Yoshinori Hitoe

Tetsuaki Okahiro

Hirokazu Takahashi

Akira Sato

Soichi Sato

Tsuyoshi Oguchi

Shinichi Fujinoki

Shigeyuki Sasanuma

Makoto Morishita

Arata Kato

Shigeo Suzuki

Shinya Miyakawa

Takaharu Tsutsumi

Tota Hasegawa

Takuya Sugino

Hiroyuki Hozumi

Kotaro Fujiyama

Masanobu Watanabe

Toshihiro Yasuda

Akira Tanokura

Akira Hamauzu

Kenjiro Fujimoto

Shigeru Takaya

Masahiro Ishimori

Yuki Minato

Tadahiro Mitsuhashi

Takashi Nakai

Yuusuke Watanabe

Hisanobu Ohkawa

Osamu Ueda

Yoshitaka Uto

Yumiko Watanabe

Yasuto Ishikawa

Hajime Mori

Yasuo Morishima

Yasushi Honda

Masahiko Warashina

Mitsuru Chiba

Tomonori Hayashi

An information learning apparatus includes a memory and a processor configured to perform generating, for each of processing units constituting an input sequence included in training data, a third embedded vector based on a first embedded vector for the processing unit and a second embedded vector corresponding to an unknown word; executing a process based on a learning target parameter, with the third embedded vector generated for each of the processing units as an input; and learning, for a processing result by the executing, the parameter based on an error of an output corresponding to the input sequence in the training data.

Embedding an unknown word in an input sequence

Disclosed is a natural language processing technique according to a neural network of high interpretive ability. One embodiment of the present disclosure relates to an apparatus including a trained neural network into which first natural language text is input and that is trained to output second natural language text and alignment information, the second natural language text being in accordance with a predetermined purpose corresponding to the first natural language text, and the alignment information indicating, for each part of the second natural language text, which part of the first natural language text is a basis of information for generation; and an analyzing unit configured to output, upon input text being input into the trained neural network, a predicted result of output text in accordance with a predetermined purpose, and alignment information indicating, for each part of the predicted result of the output text, which part of the input text is a basis of information for generation.

Device, method and program for natural language processing

Computer screen with graphical user interface

This disclosure relates to a device, a method, and a program capable of removing erroneous data from learning data used for machine learning used in natural language processing, for example. The method includes storing a forward direction learned model of a discrete series converter. The model is trained based on a plurality of pairs of discrete series of texts. Each pair comprises a first discrete series indicates an input of discrete series. A second discrete series indicates an output of discrete series. The first discrete series and the second discrete series are correctly associated. The method further includes converting the first discrete series to the second discrete series, and generating a quality score using the forward direction learned model, using a second learning pair of discrete series texts including an error in relationship.

Learning quality estimation device, method, and program

An object of the present disclosure is to provide a transmitting-side relay apparatus, a system, a method, and a program, each adapted to reduce congestions in a network while appropriately using a communication resource for a network-based communication. A transmitting-side relay apparatus according to the present disclosure includes a request rate calculation unit configured to calculate, based on a transmission rate of an input packet, an encoding loss rate at the time of encoding the input packet to generate an encoded packet, and a packet loss rate of the encoded packet in a receiving-side relay apparatus, a request rate of the encoded packet; a permissible rate calculation unit configured to calculate, based on at least one of a delay time indicating a time period from the time of generation of the input packet to the time of reception of the encoded packet.

Transmitting-side relay apparatus, system, method, and non-transitory computer-readable medium

Provided are an adhesive resin composition having high adhesiveness and high strength in acid resistance, and a laminate including the same. Provided is an adhesive resin composition including an acid-modified polyolefin resin component (A) having a weight average molecular weight of 30,000 or more and 150,000 or less, a resin component (B) having an epoxy group in a molecule, a resin component (C) having an amino group at a molecular end, and a solvent (S), in which a content of the resin component (B) is 1 part by mass or more and 30 parts by mass or less based on 100 parts by mass of the acid-modified polyolefin resin component (A), and a content of the resin component (C) is 0.5 parts by mass or more and 15 parts by mass or less based on 100 parts by mass of the acid-modified polyolefin resin component (A).

Adhesive resin composition and laminate

A display device that includes a plurality of light-emitting elements, a first light-absorbing layer having an opening at a position that faces the light-emitting elements, and a second light-absorbing layer that faces the first light-absorbing layer with the light-emitting elements therebetween.

Display device

It is possible to achieve high analysis accuracy on the whole irrespective of a coverage ratio of a morpheme dictionary. A morpheme prediction sectionoutputs a morpheme label string as a morphological analysis result of input text by inputting a resultant vector generated for each character by a vector combination sectioninto a series predictor and sequentially performing calculation. At this point, there is used the series predictor which is subjected to learning in advance such that a morpheme label string obtained by inputting a resultant vector in which a character vector and a morpheme information vector are combined and which is generated without being combined with the morpheme information vector with a specific probability into the series predictor and sequentially performing the calculation coincides with a morpheme label string of learning data.

Morpheme analysis learning device, morpheme analysis device, method, and program

A rule storing unit stores a set of rules each defining facts and a relation between the facts, and weights representing importance levels of the rules. An input data storing unit stores input data. A query storing unit stores a query. An importance level calculating unit calculates an importance level of each fact type of the facts defined by the rules. A fact data generating unit generates, for each fact type, fact data in which true/false is observed as a fact by a number corresponding to the importance level of the fact type, from the input data. A fact data storing unit stores the fact data. An inference performing unit performs probabilistic inference of a result of the query by using the fact data, the rules, and the weights. An output unit outputs a result of the inference.

Inference system

Provided are a connection management mechanism and a connection management method with which computer bus connections can be managed such that failures and freezes do not occur in a computer system when delays and packet losses occur. A connection management unit, which is used in computer bus communication in which packets are transmitted between a request source and a request destination, has a dummy return packet generation/transmission function wherein a dummy return packet is generated and is transmitted to the request source when a delay or loss occurs in a return packet transmitted from the request destination, and/or a filter function wherein, after transmission of the dummy return packet, a legitimate return packet arriving from the request destination is discarded.

Connection management unit and connection management method

A configuration management device provided with: a configuration storage means for storing a bridge that includes a virtual bridge and the configuration information of input/output devices; a bus recognition means for reading the configuration information of input/output devices connected to the bridge from the input/output devices and storing the read information in the configuration storage means; a virtual resource definition storage means for defining a virtual connection between the input/output devices connected to a connection means that is not the bridge and the virtual bridge; and a device access transfer means for receiving a configuration information read request for input/output devices connected to the virtual bridge that is transmitted by the bus recognition means, reading the configuration information from the input/output devices the virtual connection of which is defined, and transmitting the read configuration information to the bus recognition means.

Configuration management device, configuration management system, configuration management method, and non-transitory computer readable storage medium

An input/output process allocation control device includes: allocation unit that, in a case where a second information processing resource element different from a first information processing resource element executes an input/output-data-transmission/reception-process with an input/output device in response to an access request to the input/output device by the first information processing resource element, the first and second information processing resource elements being among a plurality of information processing resource elements included in an information processing apparatus, allocates the input/output-data-transmission/reception-process to the second information processing resource element and excluding the second information processing resource element, of the plurality of information processing resource elements, from a new allocation destination of a process including an access request to the input/output device.

Input/output process allocation control device, input/output process allocation control method, and recording medium having input/output process allocation control program stored therein

Growing community of inventors

Tokyo, Japan

Jun Suzuki