Title | ||
---|---|---|
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task. |
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% M$^2$ 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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.18653/v1/N18-1055 | north american chapter of the association for computational linguistics |
DocType | Volume | Citations |
Journal | abs/1804.05940 | 6 |
PageRank | References | Authors |
0.48 | 23 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcin Junczys-Dowmunt | 1 | 312 | 24.24 |
Roman Grundkiewicz | 2 | 109 | 11.75 |
Shubha Guha | 3 | 6 | 0.48 |
Kenneth Heafield | 4 | 7 | 1.86 |