Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Hyunsoo | - |
dc.contributor.author | Park, Choonghyun | - |
dc.contributor.author | Kang, Jaewook | - |
dc.contributor.author | Yoo, Kang Min | - |
dc.contributor.author | Kim, Tae Uk | - |
dc.contributor.author | Lee, Sang-goo | - |
dc.date.accessioned | 2023-08-01T07:08:12Z | - |
dc.date.available | 2023-08-01T07:08:12Z | - |
dc.date.created | 2023-07-21 | - |
dc.date.issued | 2022-12 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188683 | - |
dc.description.abstract | Out-of-distribution (OOD) detection aims todiscern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. Most recentstudies in OOD detection utilize the information from a single representation that residesin the penultimate layer to determine whetherthe input is anomalous or not. Although sucha method is straightforward, the potential ofdiverse information in the intermediate layersis overlooked. In this paper, we propose a novelframework based on contrastive learning thatencourages intermediate features to learn layerspecialized representations and assembles themimplicitly into a single representation to absorbrich information in the pre-trained languagemodel. Extensive experiments in various intentclassification and OOD datasets demonstratethat our approach is significantly more effective than other works. The source code for ourmodel is available online. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Association for Computational Linguistics | - |
dc.title | Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Tae Uk | - |
dc.identifier.bibliographicCitation | Empirical Methods in Natural Language Processing, pp.783 - 798 | - |
dc.relation.isPartOf | Empirical Methods in Natural Language Processing | - |
dc.citation.title | Empirical Methods in Natural Language Processing | - |
dc.citation.startPage | 783 | - |
dc.citation.endPage | 798 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceeding | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | other | - |
dc.identifier.url | https://aclanthology.org/2022.findings-emnlp.55.pdf | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.