The CUED’s Grammatical Error Correction Systems for BEA-2019

Felix Stahlberg, Bill Byrne

[How to correct problems with metadata yourself]


Abstract
We describe two entries from the Cambridge University Engineering Department to the BEA 2019 Shared Task on grammatical error correction. Our submission to the low-resource track is based on prior work on using finite state transducers together with strong neural language models. Our system for the restricted track is a purely neural system consisting of neural language models and neural machine translation models trained with back-translation and a combination of checkpoint averaging and fine-tuning – without the help of any additional tools like spell checkers. The latter system has been used inside a separate system combination entry in cooperation with the Cambridge University Computer Lab.
Anthology ID:
W19-4417
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:
168–175
Language:
URL:
https://aclanthology.org/W19-4417
DOI:
10.18653/v1/W19-4417
Bibkey:
Cite (ACL):
Felix Stahlberg and Bill Byrne. 2019. The CUED’s Grammatical Error Correction Systems for BEA-2019. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 168–175, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
The CUED’s Grammatical Error Correction Systems for BEA-2019 (Stahlberg & Byrne, BEA 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/W19-4417.pdf
Data
CoNLL-2014 Shared Task: Grammatical Error Correction