Artificial Error Generation with Fluency Filtering

Mengyang Qiu, Jungyeul Park


Abstract
The quantity and quality of training data plays a crucial role in grammatical error correction (GEC). However, due to the fact that obtaining human-annotated GEC data is both time-consuming and expensive, several studies have focused on generating artificial error sentences to boost training data for grammatical error correction, and shown significantly better performance. The present study explores how fluency filtering can affect the quality of artificial errors. By comparing artificial data filtered by different levels of fluency, we find that artificial error sentences with low fluency can greatly facilitate error correction, while high fluency errors introduce more noise.
Anthology ID:
W19-4408
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:
87–91
Language:
URL:
https://aclanthology.org/W19-4408
DOI:
10.18653/v1/W19-4408
Bibkey:
Cite (ACL):
Mengyang Qiu and Jungyeul Park. 2019. Artificial Error Generation with Fluency Filtering. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 87–91, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Artificial Error Generation with Fluency Filtering (Qiu & Park, BEA 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4408.pdf