Abstract
Modern writing assistance applications are always equipped with a Grammatical Error Correction (GEC) model to correct errors in user-entered sentences. Different scenarios have varying requirements for correction behavior, e.g., performing more precise corrections (high precision) or providing more candidates for users (high recall). However, previous works adjust such trade-off only for sequence labeling approaches. In this paper, we propose a simple yet effective counterpart – Align-and-Predict Decoding (APD) for the most popular sequence-to-sequence models to offer more flexibility for the precision-recall trade-off. During inference, APD aligns the already generated sequence with input and adjusts scores of the following tokens. Experiments in both English and Chinese GEC benchmarks show that our approach not only adapts a single model to precision-oriented and recall-oriented inference, but also maximizes its potential to achieve state-of-the-art results. Our code is available at https://github.com/AutoTemp/Align-and-Predict.- Anthology ID:
- 2022.acl-short.77
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 686–693
- Language:
- URL:
- https://aclanthology.org/2022.acl-short.77
- DOI:
- 10.18653/v1/2022.acl-short.77
- Cite (ACL):
- Xin Sun and Houfeng Wang. 2022. Adjusting the Precision-Recall Trade-Off with Align-and-Predict Decoding for Grammatical Error Correction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 686–693, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Adjusting the Precision-Recall Trade-Off with Align-and-Predict Decoding for Grammatical Error Correction (Sun & Wang, ACL 2022)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2022.acl-short.77.pdf
- Code
- autotemp/align-and-predict