Paraphrase thought: Sentence embedding module imitating human language recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jang, Myeongjun | - |
dc.contributor.author | Kang, Pilsung | - |
dc.date.accessioned | 2021-08-30T07:12:32Z | - |
dc.date.available | 2021-08-30T07:12:32Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2020-12 | - |
dc.identifier.issn | 0020-0255 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/51406 | - |
dc.description.abstract | Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for various natural language processing tasks, such as machine translation and document classification. Thus far, various sentence embedding models have been proposed, and their feasibility has been demonstrated through good performances on tasks following embedding, such as sentiment analysis and sentence classification. However, because the performances of sentence classification and sentiment analysis can be enhanced by using a simple sentence representation method, it is not sufficient to claim that these models fully reflect the meanings of sentences based on good performances for such tasks. In this paper, inspired by human language recognition, we propose the following concept of semantic coherence, which should be satisfied for a good sentence embedding method: similar sentences should be located close to each other in the embedding space. Then, we propose the Paraphrase-Thought (P-thought) model to pursue semantic coherence as much as possible. Experimental results on three paraphrase identification datasets (MS COCO, STS benchmark, SICK) show that the P-thought models outperform the benchmarked sentence embedding methods. (C) 2020 Elsevier Inc. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCIENCE INC | - |
dc.title | Paraphrase thought: Sentence embedding module imitating human language recognition | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kang, Pilsung | - |
dc.identifier.doi | 10.1016/j.ins.2020.05.129 | - |
dc.identifier.scopusid | 2-s2.0-85087589799 | - |
dc.identifier.wosid | 000573604900007 | - |
dc.identifier.bibliographicCitation | INFORMATION SCIENCES, v.541, pp.123 - 135 | - |
dc.relation.isPartOf | INFORMATION SCIENCES | - |
dc.citation.title | INFORMATION SCIENCES | - |
dc.citation.volume | 541 | - |
dc.citation.startPage | 123 | - |
dc.citation.endPage | 135 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.subject.keywordAuthor | Sentence embedding | - |
dc.subject.keywordAuthor | Recurrent neural network | - |
dc.subject.keywordAuthor | Paraphrase | - |
dc.subject.keywordAuthor | Semantic coherence | - |
dc.subject.keywordAuthor | Natural language processing | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.