Papers by Ali Hatami
Analysing the Correlation between Lexical Ambiguity and Translation Quality in a Multimodal Setting using WordNet (2022.naacl-srw)
Copied to clipboard
| Challenge: | Recent studies in machine translation have been focusing on using visual information to improve the translation quality of sentences. |
| Approach: | They propose to use visual information to improve the output quality of a text-based translation model by extracting ambiguity scores from WordNet. |
| Outcome: | The proposed model improves translation quality for all sentences in the English-German dataset. |