Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition
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.
Cite
@article{arxiv.2107.11610,
title = {Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition},
author = {Abbas Ghaddar and Philippe Langlais and Ahmad Rashid and Mehdi Rezagholizadeh},
journal= {arXiv preprint arXiv:2107.11610},
year = {2021}
}
Comments
MIT Press\TACL 2021\Presented at ACL 2021 This is the exact same content of the TACL version, except the figures and tables are better aligned