Semantically-Informed Syntactic Machine Translation: A Tree-Grafting Approach
This work addresses the challenge of enhancing translation quality for low-resource languages with different word orders, showing large gains through combined syntactic and semantic approaches.
The paper tackled the problem of improving statistical machine translation by integrating semantic information into syntactic frameworks, resulting in a system that significantly outperformed a baseline and achieved the highest scores on the NIST 2009 Urdu-English task.
We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language training texts improved translation quality. The resulting system significantly outperformed a linguistically naive baseline model (Hiero), and reached the highest scores yet reported on the NIST 2009 Urdu-English translation task. This finding supports the hypothesis (posed by many researchers in the MT community, e.g., in DARPA GALE) that both syntactic and semantic information are critical for improving translation quality---and further demonstrates that large gains can be achieved for low-resource languages with different word order than English.