Building a State-of-the-Art Grammatical Error Correction System

Alla Rozovskaya, Dan Roth


Abstract
This paper identifies and examines the key principles underlying building a state-of-the-art grammatical error correction system. We do this by analyzing the Illinois system that placed first among seventeen teams in the recent CoNLL-2013 shared task on grammatical error correction. The system focuses on five different types of errors common among non-native English writers. We describe four design principles that are relevant for correcting all of these errors, analyze the system along these dimensions, and show how each of these dimensions contributes to the performance.
Anthology ID:
Q14-1033
Volume:
Transactions of the Association for Computational Linguistics, Volume 2
Month:
Year:
2014
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins, Lillian Lee
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
419–434
Language:
URL:
https://aclanthology.org/Q14-1033
DOI:
10.1162/tacl_a_00193
Bibkey:
Cite (ACL):
Alla Rozovskaya and Dan Roth. 2014. Building a State-of-the-Art Grammatical Error Correction System. Transactions of the Association for Computational Linguistics, 2:419–434.
Cite (Informal):
Building a State-of-the-Art Grammatical Error Correction System (Rozovskaya & Roth, TACL 2014)
Copy Citation:
PDF:
https://aclanthology.org/Q14-1033.pdf
Data
FCE