TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation

Yiming Ai, Zhiwei He, Kai Yu, Rui Wang


Abstract
Tense inconsistency frequently occurs in machine translation. However, there are few criteria to assess the model’s mastery of tense prediction from a linguistic perspective. In this paper, we present a parallel tense test set, containing French-English 552 utterances. We also introduce a corresponding benchmark, tense prediction accuracy. With the tense test set and the benchmark, researchers are able to measure the tense consistency performance of machine translation systems for the first time.
Anthology ID:
2023.acl-short.164
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1930–1941
Language:
URL:
https://aclanthology.org/2023.acl-short.164
DOI:
10.18653/v1/2023.acl-short.164
Bibkey:
Cite (ACL):
Yiming Ai, Zhiwei He, Kai Yu, and Rui Wang. 2023. TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1930–1941, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation (Ai et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2023.acl-short.164.pdf