Connecting the Dots: Towards Human-Level Grammatical Error Correction

Shamil Chollampatt, Hwee Tou Ng


Abstract
We build a grammatical error correction (GEC) system primarily based on the state-of-the-art statistical machine translation (SMT) approach, using task-specific features and tuning, and further enhance it with the modeling power of neural network joint models. The SMT-based system is weak in generalizing beyond patterns seen during training and lacks granularity below the word level. To address this issue, we incorporate a character-level SMT component targeting the misspelled words that the original SMT-based system fails to correct. Our final system achieves 53.14% F 0.5 score on the benchmark CoNLL-2014 test set, an improvement of 3.62% F 0.5 over the best previous published score.
Anthology ID:
W17-5037
Volume:
Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Joel Tetreault, Jill Burstein, Claudia Leacock, Helen Yannakoudakis
Venue:
BEA
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
327–333
Language:
URL:
https://aclanthology.org/W17-5037
DOI:
10.18653/v1/W17-5037
Bibkey:
Cite (ACL):
Shamil Chollampatt and Hwee Tou Ng. 2017. Connecting the Dots: Towards Human-Level Grammatical Error Correction. In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pages 327–333, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Connecting the Dots: Towards Human-Level Grammatical Error Correction (Chollampatt & Ng, BEA 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5037.pdf
Data
CoNLL-2014 Shared Task: Grammatical Error CorrectionJFLEG