Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation
This work addresses grammatical error correction for language learners or writers, but it is incremental as it hybridizes existing methods.
The authors tackled grammatical error correction by combining statistical and neural machine translation approaches, achieving new state-of-the-art results on CoNLL-2014 and JFLEG benchmarks and nearing human-level performance.
We combine two of the most popular approaches to automated Grammatical Error Correction (GEC): GEC based on Statistical Machine Translation (SMT) and GEC based on Neural Machine Translation (NMT). The hybrid system achieves new state-of-the-art results on the CoNLL-2014 and JFLEG benchmarks. This GEC system preserves the accuracy of SMT output and, at the same time, generates more fluent sentences as it typical for NMT. Our analysis shows that the created systems are closer to reaching human-level performance than any other GEC system reported so far.