JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction
TL
TL;DR
A new parallel corpus, JHU FLuency-Extended GUG corpus (JFLEG), which represents a broad range of language proficiency levels and uses holistic fluency edits to not only correct grammatical errors but also make the original text more native sounding.
Abstract
We present a new parallel corpus, JHU FLuency-Extended GUG corpus (JFLEG) for developing and evaluating grammatical error correction (GEC). Unlike other corpora, it represents a broad range of language proficiency levels and uses holistic fluency edits to not only correct grammatical errors but also make the original text more native sounding. We describe the types of corrections made and benchmark four leading GEC systems on this corpus, identifying specific areas in which they do well and how they can improve. JFLEG fulfills the need for a new gold standard to properly assess the current state of GEC.
References17 items
1
Adapting Grammatical Error Correction Based on the Native Language of Writers with Neural Network Joint Models
2
Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality
3
Grammatical error correction using neural machine translation
4
Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction
5