DSpace Repository

Semantically Readable Distributed Representation Learning and Its Expandability Using a Word Semantic Vector Dictionary

Show simple item record

dc.contributor.author KESHI, Ikuo
dc.contributor.author SUZUKI, Yu
dc.contributor.author YOSHINO, Koichiro
dc.contributor.author NAKAMURA, Satoshi
dc.date.accessioned 2018-04-11T01:48:50Z
dc.date.available 2018-04-11T01:48:50Z
dc.date.issued 2018-04-01
dc.identifier.issn 0916-8532
dc.identifier.uri http://hdl.handle.net/10061/12334
dc.description.abstract The problem with distributed representations generated by neural networks is that the meaning of the features is difficult to understand. We propose a new method that gives a specific meaning to each node of a hidden layer by introducing a manually created word semantic vector dictionary into the initial weights and by using paragraph vector models. We conducted experiments to test the hypotheses using a single domain benchmark for Japanese Twitter sentiment analysis and then evaluated the expandability of the method using a diverse and large-scale benchmark. Moreover, we tested the domain-independence of the method using a Wikipedia corpus. Our experimental results demonstrated that the learned vector is better than the performance of the existing paragraph vector in the evaluation of the Twitter sentiment analysis task using the single domain benchmark. Also, we determined the readability of document embeddings, which means distributed representations of documents, in a user test. The definition of readability in this paper is that people can understand the meaning of large weighted features of distributed representations. A total of 52.4% of the top five weighted hidden nodes were related to tweets where one of the paragraph vector models learned the document embeddings. For the expandability evaluation of the method, we improved the dictionary based on the results of the hypothesis test and examined the relationship of the readability of learned word vectors and the task accuracy of Twitter sentiment analysis using the diverse and large-scale benchmark. We also conducted a word similarity task using the Wikipedia corpus to test the domain-independence of the method. We found the expandability results of the method are better than or comparable to the performance of the paragraph vector. Also, the objective and subjective evaluation support each hidden node maintaining a specific meaning. Thus, the proposed method succeeded in improving readability. ja_JP
dc.language.iso en ja_JP
dc.publisher The Institute of Electronics, Information and Communication Engineers ja_JP
dc.rights Copyright c 2018 The Institute of Electronics, Information and Communication Engineers ja_JP
dc.subject distributed representation ja_JP
dc.subject word semantic vector dictionary ja_JP
dc.subject paragraph vector ja_JP
dc.subject word2vec ja_JP
dc.subject Twitter ja_JP
dc.subject sentiment analysis, ja_JP
dc.title Semantically Readable Distributed Representation Learning and Its Expandability Using a Word Semantic Vector Dictionary ja_JP
dc.type.nii Journal Article ja_JP
dc.contributor.transcription ケシ, イクオ
dc.contributor.transcription スズキ, ユウ
dc.contributor.transcription ヨシノ, コウイチロウ
dc.contributor.transcription ナカムラ, サトシ
dc.contributor.alternative 芥子, 育雄
dc.contributor.alternative 鈴木, 優
dc.contributor.alternative 吉野 , 幸一郎
dc.contributor.alternative 中村, 哲
dc.identifier.fulltexturl https://www.jstage.jst.go.jp/article/transinf/E101.D/4/E101.D_2017DAP0019/_article/-char/ja/ ja_JP
dc.textversion publisher ja_JP
dc.identifier.jtitle IEICE Transactions on Information and Systems ja_JP
dc.identifier.volume E101.D ja_JP
dc.identifier.issue 4 ja_JP
dc.identifier.spage 1066 ja_JP
dc.identifier.epage 1078 ja_JP
dc.relation.doi info:doi/10.1587/transinf.2017DAP0019 ja_JP
dc.identifier.NAIST-ID 84369982 ja_JP
dc.identifier.NAIST-ID 74651399 ja_JP
dc.identifier.NAIST-ID 74651712 ja_JP
dc.identifier.NAIST-ID 73296626 ja_JP


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account