Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jin, Kyohoon | - |
dc.contributor.author | Lee, Junho | - |
dc.contributor.author | Choi, Juhwan | - |
dc.contributor.author | Song, Sangmin | - |
dc.contributor.author | Kim, Youngbin | - |
dc.date.accessioned | 2024-07-02T06:30:52Z | - |
dc.date.available | 2024-07-02T06:30:52Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/74531 | - |
dc.description.abstract | Efforts to leverage deep learning models in low-resource regimes have led to numerous augmentation studies. However, the direct application of methods such as mixup and cutout to text data, is limited due to their discrete characteristics. While methods using pretrained language models have exhibited efficiency, they require additional considerations for robustness. Inspired by recent studies on decision boundaries, this paper proposes a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models. The proposed technique first focuses on shifting the latent features closer to the decision boundary, followed by reconstruction to generate an ambiguous version with a soft label. Additionally, mid-K sampling is suggested to enhance the diversity of the generated sentences. This paper demonstrates the performance of the proposed augmentation strategy compared to other methods through extensive experiments. Furthermore, the ablation study reveals the effect of soft labels and mid-K sampling and the extensibility of the method with curriculum data augmentation. © 2024 ELRA Language Resource Association: CC BY-NC 4.0. | - |
dc.format.extent | 14 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | European Language Resources Association (ELRA) | - |
dc.title | Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation | - |
dc.type | Article | - |
dc.identifier.bibliographicCitation | 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings, pp 5930 - 5943 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85195898699 | - |
dc.citation.endPage | 5943 | - |
dc.citation.startPage | 5930 | - |
dc.citation.title | 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings | - |
dc.type.docType | Conference paper | - |
dc.subject.keywordAuthor | Data Augmentation | - |
dc.subject.keywordAuthor | Decision Boundary | - |
dc.subject.keywordAuthor | Robustness | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang 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.