Abstract
Most recent works in the field of grammatical error correction (GEC) rely on neural machine translation-based models. Although these models boast impressive performance, they require a massive amount of data to properly train. Furthermore, NMT-based systems treat GEC purely as a translation task and overlook the editing aspect of it. In this work we propose a heterogeneous approach to Chinese GEC, composed of a NMT-based model, a sequence editing model, and a spell checker. Our methodology not only achieves a new state-of-the-art performance for Chinese GEC, but also does so without relying on data augmentation or GEC-specific architecture changes. We further experiment with all possible configurations of our system with respect to model composition order and number of rounds of correction. A detailed analysis of each model and their contributions to the correction process is performed by adapting the ERRANT scorer to be able to score Chinese sentences.- Anthology ID:
- 2020.coling-main.199
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 2191–2201
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.199
- DOI:
- 10.18653/v1/2020.coling-main.199
- Cite (ACL):
- Charles Hinson, Hen-Hsen Huang, and Hsin-Hsi Chen. 2020. Heterogeneous Recycle Generation for Chinese Grammatical Error Correction. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2191–2201, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- Heterogeneous Recycle Generation for Chinese Grammatical Error Correction (Hinson et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.coling-main.199.pdf