Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP
- Authors
- Kim, Hyuhng Joon; Cho, Hyunsoo; Lee, Sang-Woo; Kim, Junyeob; Lee, Sang-Goo; Park, Choonghyun; Yoo, Kang Min; Kim, Taeuk
- Issue Date
- Dec-2023
- Publisher
- Association for Computational Linguistics (ACL)
- Citation
- Findings of the Association for Computational Linguistics: EMNLP 2023, pp 5888 - 5905
- Pages
- 18
- Indexed
- SCOPUS
- Journal Title
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Start Page
- 5888
- End Page
- 5905
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/194767
- ISSN
- 0000-0000
- 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.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.