| アイテムタイプ |
会議発表論文 / Conference Paper(1) |
| 公開日 |
2025-06-04 |
| タイトル |
|
|
タイトル |
Improving Self-training with Prototypical Learning for Source-Free Domain Adaptation on Clinical Text |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ |
conference paper |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
Shimizu, Seiji
矢田, 竣太郎
Raithel, Lisa
荒牧, 英治
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Domain adaptation is crucial in the clinical domain since the performance of a model trained on one domain (source) degrades seriously when applied to another domain (target). However, conventional domain adaptation methods often cannot be applied due to data sharing restrictions on source data. Source-Free Domain Adaptation (SFDA) addresses this issue by only utilizing a source model and unlabeled target data to adapt to the target domain. In SFDA, self-training is the most widely applied method involving retraining models with target data using predictions from the source model as pseudo-labels. Nevertheless, this approach is prone to contain substantial numbers of errors in pseudo-labeling and might limit model performance in the target domain. In this paper, we propose a Source-Free Prototype-based Self-training (SFPS) aiming to improve the performance of self-training. SFPS generates prototypes without accessing source data and utilizes them for prototypical learning, namely prototype-based pseudo-labeling and contrastive learning. Also, we compare entropy-based, centroid-based, and class-weights-based prototype generation methods to identify the most effective formulation of the proposed method. Experimental results across various datasets demonstrate the effectiveness of the proposed method, consistently outperforming vanilla self-training. The comparison of various prototype-generation methods identifies the most reliable generation method that improves the source model persistently. Additionally, our analysis illustrates SFPS can successfully alleviate errors in pseudo-labeling. |
| 書誌情報 |
en : Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
p. 1-13,
発行日 2024-08-16
|
| 会議情報 |
|
|
|
会議名 |
BioNLP 2024 |
|
|
開始年 |
2024 |
|
|
開始月 |
08 |
|
|
開始日 |
16 |
|
|
終了年 |
2024 |
|
|
終了月 |
08 |
|
|
終了日 |
16 |
|
|
開催地 |
Bangkok, Thailand |
|
開催国 |
THA |
| 出版者 |
|
|
出版者 |
Association for Computational Linguistics |
| 出版者版DOI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.18653/v1/2024.bionlp-1.1 |
| 出版者版URI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://aclanthology.org/2024.bionlp-1.1/ |
| 権利 |
|
|
権利情報Resource |
https://creativecommons.org/licenses/by/4.0/ |
|
権利情報 |
$00A92024 Association for Computational Linguistics |
| 著者版フラグ |
|
|
出版タイプ |
NA |
| 助成情報 |
|
|
|
助成機関名 |
Japan Science and Technology Agency(JST), CREST |
|
|
研究課題番号 |
JPMJCR22N1 |
|
|
研究課題名 |
リアルワールドテキスト処理の深化によるデータ駆動型探薬 |
| 助成情報 |
|
|
|
助成機関名 |
NCGM |
|
|
研究課題番号 |
JPJ012425 |
|
|
研究課題名 |
Cross-ministerial Strategic Innovation Promotion Program (SIP) on “Integrated Health Care System” |
| 助成情報 |
|
|
|
助成機関名 |
German Research Foundation (DFG) |
|
|
研究課題番号 |
DFG-442445488 |
|
|
研究課題名 |
Knowledge-enhanced information extraction across languages for pharmacovigilance |
| 助成情報 |
|
|
|
助成機関名 |
German Federal Ministry of Education and Research |
|
|
研究課題番号 |
BIFOLD24B |
