Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition

Abbas Ghaddar, Philippe Langlais, Ahmad Rashid, Mehdi Rezagholizadeh


Abstract
Abstract In this work, we examine the ability of NER models to use contextual information when predicting the type of an ambiguous entity. We introduce NRB, a new testbed carefully designed to diagnose Name Regularity Bias of NER models. Our results indicate that all state-of-the-art models we tested show such a bias; BERT fine-tuned models significantly outperforming feature-based (LSTM-CRF) ones on NRB, despite having comparable (sometimes lower) performance on standard benchmarks. To mitigate this bias, we propose a novel model-agnostic training method that adds learnable adversarial noise to some entity mentions, thus enforcing models to focus more strongly on the contextual signal, leading to significant gains on NRB. Combining it with two other training strategies, data augmentation and parameter freezing, leads to further gains.
Anthology ID:
2021.tacl-1.36
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
586–604
Language:
URL:
https://aclanthology.org/2021.tacl-1.36
DOI:
10.1162/tacl_a_00386
Bibkey:
Cite (ACL):
Abbas Ghaddar, Philippe Langlais, Ahmad Rashid, and Mehdi Rezagholizadeh. 2021. Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition. Transactions of the Association for Computational Linguistics, 9:586–604.
Cite (Informal):
Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition (Ghaddar et al., TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.36.pdf