Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples

Lihao Wang, Xiaoqing Zheng


Abstract
A sequence-to-sequence (seq2seq) learning with neural networks empirically shows to be an effective framework for grammatical error correction (GEC), which takes a sentence with errors as input and outputs the corrected one. However, the performance of GEC models with the seq2seq framework heavily relies on the size and quality of the corpus on hand. We propose a method inspired by adversarial training to generate more meaningful and valuable training examples by continually identifying the weak spots of a model, and to enhance the model by gradually adding the generated adversarial examples to the training set. Extensive experimental results show that such adversarial training can improve both the generalization and robustness of GEC models.
Anthology ID:
2020.emnlp-main.228
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2858–2869
Language:
URL:
https://aclanthology.org/2020.emnlp-main.228
DOI:
10.18653/v1/2020.emnlp-main.228
Bibkey:
Cite (ACL):
Lihao Wang and Xiaoqing Zheng. 2020. Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2858–2869, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples (Wang & Zheng, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.228.pdf
Video:
 https://slideslive.com/38939097