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

NAACL 2018  ·  Roman Grundkiewicz, Marcin Junczys-Dowmunt ·

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.

PDF Abstract NAACL 2018 PDF NAACL 2018 Abstract

Code
Add Remove Mark official

No code implementations yet. Submit your code now
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Grammatical Error Correction CoNLL-2014 Shared Task SMT + BiGRU F0.5 56.25 # 17
Compare
Grammatical Error Correction CoNLL-2014 Shared Task (10 annotations) SMT + BiGRU F0.5 72.04 # 2
Compare
Grammatical Error Correction JFLEG SMT + BiGRU GLEU 61.5 # 3
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy