公开(公告)号：US20210326675A1

公开(公告)日：2021-10-21

申请号：US17252809

申请日：2019-06-18

申请人： National Institute of Information and Communications Technology

发明人： Jonghoon OH ,  Kentaro TORISAWA ,  Canasai KRUENGKRAI ,  Julien KLOETZER ,  Ryu IIDA ,  Ryo ISHIDA ,  Yoshihiko ASAO

IPC分类号： G06N3/04 ,  G06N3/08

摘要： A memory for a question-answering device that reduces influence of noise on answer generation and is capable of generating highly accurate answers includes: a memory configured to normalize vector expressions of answers included in a set of answers extracted from a prescribed background knowledge source for each of a plurality of mutually different questions and to store the results as normalized vectors; and a key-value memory access unit responsive to application of a question vector derived from a question for accessing the memory and for updating the question vector by using a degree of relatedness between the question vector and the plurality of questions and using the normalized vectors corresponding to respective ones of the plurality of questions.

公开(公告)号：US20170242915A1

公开(公告)日：2017-08-24

申请号：US15503553

申请日：2015-08-10

申请人： National Institute of Information and Communications Technology

发明人： Kentaro TORISAWA ,  Jun GOTO ,  Julien KLOETZER ,  Takuya KAWADA

IPC分类号： G06F17/30

CPC分类号： G06F16/3329 ,  G06F16/00 ,  G06F16/3344 ,  G06F16/338

摘要： [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 word 480 as a source for generating a question sentence; and question sentence generating database 502 comprised 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 506, searching the question sentence generating database 502 for an answer sentence pattern using the word 480 received by the word receiving means as a key, for generating a question sentence from a retrieved answer sentence pattern and the received word 480.

公开(公告)号：US20230385558A1

公开(公告)日：2023-11-30

申请号：US18031740

申请日：2021-10-13

申请人： National Institute of Information and Communications Technology

发明人： Jonghoon OH ,  Kentaro TORISAWA ,  Julien KLOETZER ,  Ryu IIDA

IPC分类号： G06F40/40 ,  G06F16/35 ,  G06F16/332

CPC分类号： G06F40/40 ,  G06F16/35 ,  G06F16/3329

摘要： A text classifier 90 for answer identification is capable of highly accurate identification of an answer candidate to a question, by effectively using background knowledge related to the question, in order to extract an answer candidate to the question, the text classifier including: a BERT (Bidirectional Encoder Representation from Transformers) receiving a question and an answer candidate as inputs; a knowledge integration transformer receiving the output of BERT as an input; a background knowledge representation generator receiving a question and an answer as inputs and generating a group of background knowledge representation vectors for the question; and a vector converter respectively converting the question and the answer candidate to embedded vectors and inputting the same to the background knowledge representation generator. The knowledge integration transformer receives the group of background knowledge representation vectors as attention and outputs a label indicating whether the answer candidate includes the correct answer to the question.

公开(公告)号：US20210034817A1

公开(公告)日：2021-02-04

申请号：US17043069

申请日：2019-03-05

申请人： National Institute of Information and Communications Technology

发明人： Yoshihiko ASAO ,  Ryu IIDA ,  Canasai KRUENGKRAI ,  Noriyuki ABE ,  Kanako ONISHI ,  Kentaro TORISAWA ,  Yutaka KIDAWARA

IPC分类号： G06F40/268 ,  G06N3/08 ,  G06N3/04 ,  G06F40/58

摘要： A request paraphrasing system 120 allowing a dialogue system to flexibly address to requests in various different manners of expression includes: a pre-processing unit 130 converting a user input 56 to a word vector sequence; and a neural paraphrasing model 94 trained 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 device 122 than the request before paraphrasing. As pre-processing, whether the user input 56 is a request or not may be determined and it may be paraphrased only when it is determined to be a request. Further, a classification model 98 may 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 94.

公开(公告)号：US20190251171A1

公开(公告)日：2019-08-15

申请号：US16331977

申请日：2017-09-25

申请人： National Institute of Information and Communications Technology

发明人： Kazuaki INADA ,  Chikara HASHIMOTO ,  Kentaro TORISAWA

IPC分类号： G06F17/27 ,  G06F16/906 ,  G06F16/2457

CPC分类号： G06F17/2785 ,  G06F16/00 ,  G06F16/24578 ,  G06F16/906 ,  G06F17/27 ,  G06N20/00

摘要： 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.

公开(公告)号：US20160260026A1

公开(公告)日：2016-09-08

申请号：US15026969

申请日：2014-10-06

申请人： NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY

发明人： Julien KLOETZER ,  Kentaro TORISAWA ,  Chikara HASHIMOTO ,  Motoki SANO ,  Jonghoon OH ,  Kiyonori OOTAKE

IPC分类号： G06N99/00 ,  G06N5/04

CPC分类号： G06N20/00 ,  G06F17/2785 ,  G06K9/6263 ,  G06K9/6269 ,  G06K9/72 ,  G06K2209/01 ,  G06N5/047

摘要： [Object] An object is to provide a device capable of efficiently collecting contradictory expressions in units smaller than a sentence.[Solution] A contradictory expression collecting device includes: a first-stage contradiction pattern classifying unit extracting a pattern pair consisting of mutually contradictory patterns by machine learning using as training data pattern pairs consisting of patterns in the form of “subject X predicate object Y”; an additional contradiction pattern pair deriving unit 130 deriving a new pattern pair by rewriting one pattern of each extracted pattern pair by using entailment relation; a training data expanding unit for expanding training data by adding to the training data those of the newly derived pattern pairs which are highly likely consisting of mutually contradicting patterns; and an SVM 142 performing a second-stage classification classifying given pattern pairs to pattern pairs consisting of mutually contradictory patterns and to other pairs, based on machine learning using the expanded training data.

摘要翻译： 对象是提供能够以小于句子的单位有效地收集矛盾表达的装置。 解决方案：一种矛盾表现收集装置，包括：第一阶段矛盾模式分类单元，通过机器学习提取由相互矛盾模式组成的模式对，使用由“对象X谓词对象Y”形式的模式组成的训练数据模式对， ; 附加的矛盾图案对导出单元130通过使用包含关系重写每个提取的图案对的一个图案来导出新的图案对; 训练数据扩展单元，用于通过向训练数据添加那些非常可能由相互矛盾的模式组成的新导出的模式对的扩展来扩展训练数据; 以及基于使用扩展的训练数据的机器学习，执行将给定图案对分类到由相互矛盾的图案组成的图案对和其他对的第二阶段分类的SVM 142。

公开(公告)号：US20210286948A1

公开(公告)日：2021-09-16

申请号：US16336676

申请日：2017-09-28

申请人： National Institute of Information and Communications Technology

发明人： Canasai KRUENGKRAI ,  Chikara HASHIMOTO ,  Kentaro TORISAWA ,  Julien KLOETZER ,  Jonghoon OH ,  Masahiro TANAKA

IPC分类号： G06F40/30 ,  G06N5/00 ,  G06N5/02 ,  G06N3/04 ,  G06F16/33 ,  G06F40/289

摘要： 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.

公开(公告)号：US20200233908A1

公开(公告)日：2020-07-23

申请号：US16487041

申请日：2018-03-15

申请人： National Institute of Information and Communications Technology

发明人： Noriyuki ABE ,  Kanako ONISHI ,  Kentaro TORISAWA ,  Canasai KRUENGKRAI ,  Yutaka KIDAWARA

IPC分类号： G06F16/9032 ,  G06F40/35 ,  G10L25/63

摘要： 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.

公开(公告)号：US20200183983A1

公开(公告)日：2020-06-11

申请号：US16321988

申请日：2017-07-26

申请人： National Institute of Information and Communications Technology

发明人： Noriyuki ABE ,  Kanako ONISHI ,  Kentaro TORISAWA ,  Canasai KRUENGKRAI ,  Jonghoon OH ,  Ryu IIDA ,  Yutaka KIDAWARA

IPC分类号： G06F16/9032 ,  G10L15/22 ,  G10L15/26

摘要： 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.

公开(公告)号：US20160321244A1

公开(公告)日：2016-11-03

申请号：US15104856

申请日：2014-12-17

申请人： NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY

发明人： Chikara HASHIMOTO ,  Kentaro TORISAWA ,  Motoki SANO ,  Yulan YAN ,  Yutaka KIDAWARA

IPC分类号： G06F17/27 ,  G06F17/30

CPC分类号： G06F17/2775 ,  G06F17/27 ,  G06F17/271 ,  G06F17/2755 ,  G06F17/277 ,  G06F17/2785 ,  G06F17/30604 ,  G06F17/30699

摘要： [Object] An object of the present invention is to provide a system for collecting elements as a basis for generating a social scenario useful to make well-balanced good decision.[Solution] A phrase pair collecting apparatus includes: a causality seed pair DB 410 storing seed pairs each consisting of a pair of phrases including a combination of a noun and a predicate template; a semantic relation pattern DB 400 storing semantic relation patterns between words; a word pair DB 402 storing word pairs related to any of the semantic relation patterns; a semantic relation pattern matching unit 470 for determining which of the semantic relation pattern matches a noun pair in each seed pair stored in causality seed pair DB 410; and a word pair replacing unit 472 for replacing the noun pair of a seed pair using, of the word pairs stored in the word pair DB 402, each of those word pairs which are related to the semantic relation pattern determined to be matching the noun pair, and thereby generating new hypotheses.

摘要翻译： 短语对收集装置包括：因果关系种子对DB 410，存储种子对，每个种子对由包括名词和谓词模板的组合的一对短语组成; 语义关系模式DB 400，其存储词之间的语义关系模式; 字对DB 402，其存储与任意语义关系模式相关的字对; 语义关系模式匹配单元470，用于确定语义关系模式中的哪一个与存在于因果种子对DB 410中的每个种子对中的名词对匹配; 以及字对替换单元472，用于使用存储在单词对DB 402中的单词对替换种子对的名词对，与确定为匹配名词对的语义关系模式相关的每个单词对 ，从而产生新的假设。