Diversity-Driven Combination for Grammatical Error Correction
This addresses the problem of improving grammatical error correction for language learners and writers by enhancing system combination, though it is incremental as it builds on existing combination methods.
The paper tackles the limited gains from combining similar neural network outputs in grammatical error correction by introducing a diversity-driven combination strategy, achieving significant performance improvements on CoNLL-2014 and BEA-2019 benchmarks.
Grammatical error correction (GEC) is the task of detecting and correcting errors in a written text. The idea of combining multiple system outputs has been successfully used in GEC. To achieve successful system combination, multiple component systems need to produce corrected sentences that are both diverse and of comparable quality. However, most existing state-of-the-art GEC approaches are based on similar sequence-to-sequence neural networks, so the gains are limited from combining the outputs of component systems similar to one another. In this paper, we present Diversity-Driven Combination (DDC) for GEC, a system combination strategy that encourages diversity among component systems. We evaluate our system combination strategy on the CoNLL-2014 shared task and the BEA-2019 shared task. On both benchmarks, DDC achieves significant performance gain with a small number of training examples and outperforms the component systems by a large margin. Our source code is available at https://github.com/nusnlp/gec-ddc.