Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation
Open paper
Benchmark
Model
Rank
Results
grammatical-error-correction-on-conll-2014
SMT + BiGRU
–
F0.5: 56.25
grammatical-error-correction-on-conll-2014-1
SMT + BiGRU
–
F0.5: 72.04
grammatical-error-correction-on-jfleg
SMT + BiGRU
–
GLEU: 61.5
Rank counts only results with a code link.