Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Hyuhng Joon | - |
dc.contributor.author | Cho, Hyunsoo | - |
dc.contributor.author | Lee, Sang-Woo | - |
dc.contributor.author | Kim, Junyeob | - |
dc.contributor.author | Lee, Sang-Goo | - |
dc.contributor.author | Park, Choonghyun | - |
dc.contributor.author | Yoo, Kang Min | - |
dc.contributor.author | Kim, Taeuk | - |
dc.date.accessioned | 2024-06-24T14:00:33Z | - |
dc.date.available | 2024-06-24T14:00:33Z | - |
dc.date.issued | 2023-12 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/194767 | - |
dc.description.abstract | When deploying machine learning systems to the wild, it is highly desirable for them to effectively leverage prior knowledge to the unfamiliar domain while also firing alarms to anomalous inputs. In order to address these requirements, Universal Domain Adaptation (UniDA) has emerged as a novel research area in computer vision, focusing on achieving both adaptation ability and robustness (i.e., the ability to detect out-of-distribution samples). While UniDA has led significant progress in computer vision, its application on language input still needs to be explored despite its feasibility. In this paper, we propose a comprehensive benchmark for natural language that offers thorough viewpoints of the model's generalizability and robustness. Our benchmark encompasses multiple datasets with varying difficulty levels and characteristics, including temporal shifts and diverse domains. On top of our testbed, we validate existing UniDA methods from computer vision and state-of-the-art domain adaptation techniques from NLP literature, yielding valuable findings: We observe that UniDA methods originally designed for image input can be effectively transferred to the natural language domain while also underscoring the effect of adaptation difficulty in determining the model's performance. | - |
dc.format.extent | 18 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Association for Computational Linguistics (ACL) | - |
dc.title | Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP | - |
dc.type | Article | - |
dc.identifier.scopusid | 2-s2.0-85183306182 | - |
dc.identifier.bibliographicCitation | Findings of the Association for Computational Linguistics: EMNLP 2023, pp 5888 - 5905 | - |
dc.citation.title | Findings of the Association for Computational Linguistics: EMNLP 2023 | - |
dc.citation.startPage | 5888 | - |
dc.citation.endPage | 5905 | - |
dc.type.docType | Conference paper | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Computational linguistics | - |
dc.subject.keywordPlus | Knowledge management | - |
dc.subject.keywordPlus | Learning algorithms | - |
dc.subject.keywordPlus | Learning systems | - |
dc.subject.keywordPlus | Natural language processing systems | - |
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.