Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space

Dongyu Ru, Jiangtao Feng, Lin Qiu, Hao Zhou, Mingxuan Wang, Weinan Zhang, Yong Yu, Lei Li


Abstract
Active learning for sentence understanding aims at discovering informative unlabeled data for annotation and therefore reducing the demand for labeled data. We argue that the typical uncertainty sampling method for active learning is time-consuming and can hardly work in real-time, which may lead to ineffective sample selection. We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently. AUSDS maps sentences into latent space generated by the popular pre-trained language models, and discover informative unlabeled text samples for annotation via adversarial attack. The proposed approach is extremely efficient compared with traditional uncertainty sampling with more than 10x speedup. Experimental results on five datasets show that AUSDS outperforms strong baselines on effectiveness.
Anthology ID:
2020.findings-emnlp.441
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4908–4917
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.441
DOI:
10.18653/v1/2020.findings-emnlp.441
Bibkey:
Cite (ACL):
Dongyu Ru, Jiangtao Feng, Lin Qiu, Hao Zhou, Mingxuan Wang, Weinan Zhang, Yong Yu, and Lei Li. 2020. Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4908–4917, Online. Association for Computational Linguistics.
Cite (Informal):
Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space (Ru et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.441.pdf
Data
AG NewsSSTSST-2SST-5