Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English

Ruikang Shi, Alvin Grissom II, Duc Minh Trinh


Abstract
We examine the inducement of rare but severe errors in English-Chinese and Chinese-English in-domain neural machine translation by minimal deletion of source text with character-based models. By deleting a single character, we can induce severe translation errors. We categorize these errors and compare the results of deleting single characters and single words. We also examine the effect of training data size on the number and types of pathological cases induced by these minimal perturbations, finding significant variation. We find that deleting a word hurts overall translation score more than deleting a character, but certain errors are more likely to occur when deleting characters, with language direction also influencing the effect.
Anthology ID:
2022.coling-1.459
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5175–5180
Language:
URL:
https://aclanthology.org/2022.coling-1.459
DOI:
Bibkey:
Cite (ACL):
Ruikang Shi, Alvin Grissom II, and Duc Minh Trinh. 2022. Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5175–5180, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English (Shi et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.459.pdf
Code
 shadoom7/hallucination_research