Abstract
Machine translation is widely utilized to translate text between language pairs. However, the accurate recognition and translation of the entities within input text remains a challenge. Current translation models often struggle to identify entities, leading to literal and incorrect translations in queries. This disclosure describes techniques, referred to as entity-aware (EaT) that enable machine translation models to recognize entities in source text, resulting in accurate and idiomatic translations. Per the techniques, joint translation of an input query and its associated semantic parse is performed. Semantically parsed information is used as supplementary data in a manner that enables the translation model to identify entities in the query, resulting in an overall improvement to the quality of translation. The techniques can be implemented by leveraging widely available translation models and are of low computational complexity.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Jauhari, Sarthak; Krishnakumaran, Saisuresh; Vasudevan, Dinkar; and Goel, Rahul, "Entity-aware Joint Translation of Query and Semantic Parse", Technical Disclosure Commons, (November 11, 2024)
https://www.tdcommons.org/dpubs_series/7514