期刊
NATURAL LANGUAGE ENGINEERING
卷 -, 期 -, 页码 -出版社
CAMBRIDGE UNIV PRESS
DOI: 10.1017/S1351324921000486
关键词
Tagging; Evaluation; Part-of-speech tagging; Information extraction
资金
- Thailand Graduate Institute of Science and Technology, National Science and Technology Development Agency (NSTDA) [TGIST:SCA-CO-2561-7116TH]
In this paper, an adversarial training framework is introduced to enhance the robustness of sequence labeling models against typographical adversarial examples. Extensive experiments on multiple tasks and languages demonstrate its effectiveness.
Many fundamentaltasks in natural language processing (NLP) such as part-of-speech tagging, text chunking, and named-entity recognition can be formulated as sequence labeling problems. Although neural sequence labeling models have shown excellent results on standard test sets, they are very brittle when presented with misspelled texts. In this paper, we introduce an adversarial training framework that enhances the robustness against typographical adversarial examples. We evaluate the robustness of sequence labeling models with an adversarial evaluation scheme that includes typographical adversarial examples. We generate two types of adversarial examples without access (black-box) or with full access (white-box) to the target model's parameters. We conducted a series of extensive experiments on three languages (English, Thai, and German) across three sequence labeling tasks. Experiments show that the proposed adversarial training framework provides better resistance against adversarial examples on all tasks. We found that we can further improve the model's robustness on the chunking task by including a triplet loss constraint.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据