Grammatical Error Correction through Round-Trip Machine Translation
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Grammatical Error Correction through Round-Trip Machine Translation. / Kementchedjhieva, Yova; Søgaard, Anders.
Findings of the Association for Computational Linguistics: EACL 2023. Association for Computational Linguistics (ACL), 2023. p. 2208-2215.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Grammatical Error Correction through Round-Trip Machine Translation
AU - Kementchedjhieva, Yova
AU - Søgaard, Anders
PY - 2023
Y1 - 2023
N2 - Machine translation (MT) operates on the premise of an interlingua which abstracts away from surface form while preserving meaning. A decade ago the idea of using round-trip MT to guide grammatical error correction was proposed as a way to abstract away from potential errors in surface forms (Madnani et al., 2012). At the time, it did not pan out due to the low quality of MT systems of the day. Today much stronger MT systems are available so we re-evaluate this idea across five languages and models of various sizes. We find that for extra large models input augmentation through round-trip MT has little to no effect. For more ‘workable’ model sizes, however, it yields consistent improvements, sometimes bringing the performance of a base or large model up to that of a large or xl model, respectively. The round-trip translation comes at a computational cost though, so one would have to determine whether to opt for a larger model or for input augmentation on a case-by-case basis.
AB - Machine translation (MT) operates on the premise of an interlingua which abstracts away from surface form while preserving meaning. A decade ago the idea of using round-trip MT to guide grammatical error correction was proposed as a way to abstract away from potential errors in surface forms (Madnani et al., 2012). At the time, it did not pan out due to the low quality of MT systems of the day. Today much stronger MT systems are available so we re-evaluate this idea across five languages and models of various sizes. We find that for extra large models input augmentation through round-trip MT has little to no effect. For more ‘workable’ model sizes, however, it yields consistent improvements, sometimes bringing the performance of a base or large model up to that of a large or xl model, respectively. The round-trip translation comes at a computational cost though, so one would have to determine whether to opt for a larger model or for input augmentation on a case-by-case basis.
U2 - 10.18653/v1/2023.findings-eacl.165
DO - 10.18653/v1/2023.findings-eacl.165
M3 - Article in proceedings
SP - 2208
EP - 2215
BT - Findings of the Association for Computational Linguistics: EACL 2023
PB - Association for Computational Linguistics (ACL)
T2 - 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023
Y2 - 2 May 2023 through 6 May 2023
ER -
ID: 381561609