On the Robustness of Language Encoders against Grammatical Errors

Fan Yin, Quanyu Long, Tao Meng, Kai-Wei Chang


Abstract
We conduct a thorough study to diagnose the behaviors of pre-trained language encoders (ELMo, BERT, and RoBERTa) when confronted with natural grammatical errors. Specifically, we collect real grammatical errors from non-native speakers and conduct adversarial attacks to simulate these errors on clean text data. We use this approach to facilitate debugging models on downstream applications. Results confirm that the performance of all tested models is affected but the degree of impact varies. To interpret model behaviors, we further design a linguistic acceptability task to reveal their abilities in identifying ungrammatical sentences and the position of errors. We find that fixed contextual encoders with a simple classifier trained on the prediction of sentence correctness are able to locate error positions. We also design a cloze test for BERT and discover that BERT captures the interaction between errors and specific tokens in context. Our results shed light on understanding the robustness and behaviors of language encoders against grammatical errors.
Anthology ID:
2020.acl-main.310
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3386–3403
Language:
URL:
https://aclanthology.org/2020.acl-main.310
DOI:
10.18653/v1/2020.acl-main.310
Bibkey:
Cite (ACL):
Fan Yin, Quanyu Long, Tao Meng, and Kai-Wei Chang. 2020. On the Robustness of Language Encoders against Grammatical Errors. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3386–3403, Online. Association for Computational Linguistics.
Cite (Informal):
On the Robustness of Language Encoders against Grammatical Errors (Yin et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.310.pdf
Video:
 http://slideslive.com/38929308
Code
 uclanlp/ProbeGrammarRobustness
Data
GLUEMRPCMultiNLIQNLISSTSST-2