Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation

TL;DR

This paper introduces a hybrid grammatical error correction system combining SMT and NMT approaches, achieving state-of-the-art results and approaching human-level performance in grammatical correction tasks.

Contribution

The paper presents a novel hybrid GEC system that leverages the strengths of both SMT and NMT, setting new benchmarks in accuracy and fluency.

Findings

Achieved state-of-the-art results on CoNLL-2014 and JFLEG benchmarks.

Hybrid system outperforms individual SMT or NMT systems.

Closer to human-level performance than previous GEC systems.

Abstract

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.