Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task
Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, Kenneth Heafield
Abstract
Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource neural MT and successfully adapt several methods from low-resource MT to neural GEC. We further establish guidelines for trustable results in neural GEC and propose a set of model-independent methods for neural GEC that can be easily applied in most GEC settings. Proposed methods include adding source-side noise, domain-adaptation techniques, a GEC-specific training-objective, transfer learning with monolingual data, and ensembling of independently trained GEC models and language models. The combined effects of these methods result in better than state-of-the-art neural GEC models that outperform previously best neural GEC systems by more than 10% M² on the CoNLL-2014 benchmark and 5.9% on the JFLEG test set. Non-neural state-of-the-art systems are outperformed by more than 2% on the CoNLL-2014 benchmark and by 4% on JFLEG.- Anthology ID:
- N18-1055
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 595–606
- Language:
- URL:
- https://aclanthology.org/N18-1055
- DOI:
- 10.18653/v1/N18-1055
- Cite (ACL):
- Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, and Kenneth Heafield. 2018. Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 595–606, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task (Junczys-Dowmunt et al., NAACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/N18-1055.pdf
- Code
- grammatical/neural-naacl2018
- Data
- CoNLL-2014 Shared Task: Grammatical Error Correction, FCE, JFLEG