Enhancing Machine Translation Experiences with Multilingual Knowledge Graphs
Simone Conia, Daniel Lee, Min Li, Umar Farooq Minhas, Yunyao Li
Abstract
Translating entity names, especially when a literal translation is not correct, poses a significant challenge. Although Machine Translation (MT) systems have achieved impressive results, they still struggle to translate cultural nuances and language-specific context. In this work, we show that the integration of multilingual knowledge graphs into MT systems can address this problem and bring two significant benefits: i) improving the translation of utterances that contain entities by leveraging their human-curated aliases from a multilingual knowledge graph, and, ii) increasing the interpretability of the translation process by providing the user with information from the knowledge graph.
BibTeX
@article{Conia_Lee_Li_Minhas_Li_2024, title={Enhancing Machine Translation Experiences with Multilingual Knowledge Graphs}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30563}, DOI={10.1609/aaai.v38i21.30563}, abstractNote={Translating entity names, especially when a literal translation is not correct, poses a significant challenge. Although Machine Translation (MT) systems have achieved impressive results, they still struggle to translate cultural nuances and language-specific context. In this work, we show that the integration of multilingual knowledge graphs into MT systems can address this problem and bring two significant benefits: i) improving the translation of utterances that contain entities by leveraging their human-curated aliases from a multilingual knowledge graph, and, ii) increasing the interpretability of the translation process by providing the user with information from the knowledge graph.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Conia, Simone and Lee, Daniel and Li, Min and Minhas, Umar Farooq and Li, Yunyao}, year={2024}, month={Mar.}, pages={23781-23783} }