Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2209.02145 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910332890382336 |
|---|---|
| author | Shi, Ruikang Grissom II, Alvin Trinh, Duc Minh |
| author_facet | Shi, Ruikang Grissom II, Alvin Trinh, Duc Minh |
| contents | We examine the inducement of rare but severe errors in English-Chinese and Chinese-English in-domain neural machine translation by minimal deletion of the 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_02145 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English Shi, Ruikang Grissom II, Alvin Trinh, Duc Minh Computation and Language Artificial Intelligence Machine Learning We examine the inducement of rare but severe errors in English-Chinese and Chinese-English in-domain neural machine translation by minimal deletion of the 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. |
| title | Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2209.02145 |