The LAIX Systems in the BEA-2019 GEC Shared Task

Ruobing Li, Chuan Wang, Yefei Zha, Yonghong Yu, Shiman Guo, Qiang Wang, Yang Liu, Hui Lin


Abstract
In this paper, we describe two systems we developed for the three tracks we have participated in the BEA-2019 GEC Shared Task. We investigate competitive classification models with bi-directional recurrent neural networks (Bi-RNN) and neural machine translation (NMT) models. For different tracks, we use ensemble systems to selectively combine the NMT models, the classification models, and some rules, and demonstrate that an ensemble solution can effectively improve GEC performance over single systems. Our GEC systems ranked the first in the Unrestricted Track, and the third in both the Restricted Track and the Low Resource Track.
Anthology ID:
W19-4416
Volume:
Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Helen Yannakoudakis, Ekaterina Kochmar, Claudia Leacock, Nitin Madnani, Ildikó Pilán, Torsten Zesch
Venue:
BEA
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
159–167
Language:
URL:
https://aclanthology.org/W19-4416
DOI:
10.18653/v1/W19-4416
Bibkey:
Cite (ACL):
Ruobing Li, Chuan Wang, Yefei Zha, Yonghong Yu, Shiman Guo, Qiang Wang, Yang Liu, and Hui Lin. 2019. The LAIX Systems in the BEA-2019 GEC Shared Task. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 159–167, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
The LAIX Systems in the BEA-2019 GEC Shared Task (Li et al., BEA 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4416.pdf
Data
FCEWI-LOCNESS