-
Notifications
You must be signed in to change notification settings - Fork 8
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
0 parents
commit b3b0241
Showing
1 changed file
with
18 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,18 @@ | ||
# Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses | ||
|
||
|
||
``` | ||
@article{doi:10.1162/tacl\_a\_00282, | ||
author = {Napoles, Courtney and Nădejde, Maria and Tetreault, Joel}, | ||
title = {Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses}, | ||
journal = {Transactions of the Association for Computational Linguistics}, | ||
volume = {7}, | ||
number = {}, | ||
pages = {551-566}, | ||
year = {2019}, | ||
doi = {10.1162/tacl\_a\_00282}, | ||
URL = {https://doi.org/10.1162/tacl_a_00282}, | ||
eprint = {https://doi.org/10.1162/tacl_a_00282}, | ||
abstract = { Until now, grammatical error correction (GEC) has been primarily evaluated on text written by non-native English speakers, with a focus on student essays. This paper enables GEC development on text written by native speakers by providing a new data set and metric. We present a multiple-reference test corpus for GEC that includes 4,000 sentences in two new domains (formal and informal writing by native English speakers) and 2,000 sentences from a diverse set of non-native student writing. We also collect human judgments of several GEC systems on this new test set and perform a meta-evaluation, assessing how reliable automatic metrics are across these domains. We find that commonly used GEC metrics have inconsistent performance across domains, and therefore we propose a new ensemble metric that is robust on all three domains of text.} | ||
} | ||
``` |