Examining the impact of adaptive convolution on natural language understanding
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Jun-Hyung | - |
dc.contributor.author | Choi, Byung-Ju | - |
dc.contributor.author | Lee, SangKeun | - |
dc.date.accessioned | 2022-02-10T09:40:35Z | - |
dc.date.available | 2022-02-10T09:40:35Z | - |
dc.date.created | 2022-02-09 | - |
dc.date.issued | 2022-03-01 | - |
dc.identifier.issn | 0957-4174 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/135201 | - |
dc.description.abstract | Convolutional neural networks (CNNs) have shown promising results on many natural language understanding (NLU) tasks owing to their ability to capture informative features in local patches. However, they extract informative patterns in a static manner; they use the same set of filters regardless of different inputs. In this article, we propose an adaptive convolution to provide greater flexibility to traditional CNNs. Unlike the traditional convolution, the adaptive convolution utilizes adaptively generated convolution filters which are conditioned on inputs. We achieve this by attaching filter-generating networks, which are carefully designed to generate input-specific filters, to each convolution block in existing CNNs. We show the efficacy of our approach for existing CNNs through extensive performance evaluations. Our results indicate that adaptive convolutions improve all the baselines, without any exception, by as much as 2.6 percentage points (%p) on sentiment analysis, 1.6 %p on text classification, and 3.6 %p on textual entailment. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.title | Examining the impact of adaptive convolution on natural language understanding | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, SangKeun | - |
dc.identifier.doi | 10.1016/j.eswa.2021.116044 | - |
dc.identifier.scopusid | 2-s2.0-85118491236 | - |
dc.identifier.wosid | 000720659000009 | - |
dc.identifier.bibliographicCitation | EXPERT SYSTEMS WITH APPLICATIONS, v.189 | - |
dc.relation.isPartOf | EXPERT SYSTEMS WITH APPLICATIONS | - |
dc.citation.title | EXPERT SYSTEMS WITH APPLICATIONS | - |
dc.citation.volume | 189 | - |
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.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Operations Research & Management Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Operations Research & Management Science | - |
dc.subject.keywordAuthor | Natural language understanding | - |
dc.subject.keywordAuthor | Adaptive convolution | - |
dc.subject.keywordAuthor | Network adaptation | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
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.