Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction

Piji Li, Shuming Shi


Abstract
We investigate the problem of Chinese Grammatical Error Correction (CGEC) and present a new framework named Tail-to-Tail (TtT) non-autoregressive sequence prediction to address the deep issues hidden in CGEC. Considering that most tokens are correct and can be conveyed directly from source to target, and the error positions can be estimated and corrected based on the bidirectional context information, thus we employ a BERT-initialized Transformer Encoder as the backbone model to conduct information modeling and conveying. Considering that only relying on the same position substitution cannot handle the variable-length correction cases, various operations such substitution, deletion, insertion, and local paraphrasing are required jointly. Therefore, a Conditional Random Fields (CRF) layer is stacked on the up tail to conduct non-autoregressive sequence prediction by modeling the token dependencies. Since most tokens are correct and easily to be predicted/conveyed to the target, then the models may suffer from a severe class imbalance issue. To alleviate this problem, focal loss penalty strategies are integrated into the loss functions. Moreover, besides the typical fix-length error correction datasets, we also construct a variable-length corpus to conduct experiments. Experimental results on standard datasets, especially on the variable-length datasets, demonstrate the effectiveness of TtT in terms of sentence-level Accuracy, Precision, Recall, and F1-Measure on tasks of error Detection and Correction.
Anthology ID:
2021.acl-long.385
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4973–4984
Language:
URL:
https://aclanthology.org/2021.acl-long.385
DOI:
10.18653/v1/2021.acl-long.385
Bibkey:
Cite (ACL):
Piji Li and Shuming Shi. 2021. Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4973–4984, Online. Association for Computational Linguistics.
Cite (Informal):
Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction (Li & Shi, ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.385.pdf
Video:
 https://aclanthology.org/2021.acl-long.385.mp4
Code
 lipiji/TtT