Skip to content
conftrace_
2019 ACL ACL 2019

(Almost) Unsupervised Grammatical Error Correction using Synthetic Comparable Corpus

Abstract

AbstractWe introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation. We verified our GEC system through experiments on a low resource track of the shared task at BEA2019. As a result, we achieved an F0.5 score of 28.31 points with the test data.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Satoru Katsumata, Mamoru Komachi

Topics

Machine Learning > Learning Types > Unsupervised Learning Natural Language Processing > Generation > Text Generation Deep Learning > Learning Types > Unsupervised Learning Natural Language Processing > Applications > Grammatical Error Correction

Keywords

unsupervised learning grammatical error correction statistical machine translation phrase-based translation synthetic corpus text correction
Download PDF

More from ACL 2019

All ACL 2019 papers →
Context is Key: Grammatical Error Detection with Contextual Word Representations
How to account for mispellings: Quantifying the benefit of character representations in neural content scoring models
The Unreasonable Effectiveness of Transformer Language Models in Grammatical Error Correction
Learning to combine Grammatical Error Corrections
Erroneous data generation for Grammatical Error Correction
The LAIX Systems in the BEA-2019 GEC Shared Task