Improving Seq2Seq Grammatical Error Correction via Decoding Interventions
Open paper
Benchmark
Model
Rank
Results
grammatical-error-correction-on-bea-2019-test
GEC-DI (LM+GED)
#11
F0.5: 73.1
grammatical-error-correction-on-conll-2014-shared-task
GEC-DI (LM+GED)
#4
F0.5: 69.6
Precision: 79.2
Recall: 46.8
Rank counts only results with a code link.