Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913552842883072 |
|---|---|
| author | Conia, Simone Lee, Daniel Li, Min Minhas, Umar Farooq Potdar, Saloni Li, Yunyao |
| author_facet | Conia, Simone Lee, Daniel Li, Min Minhas, Umar Farooq Potdar, Saloni Li, Yunyao |
| contents | Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages. These variations may also be caused by transcreation, an adaptation process that entails more than transliteration and word-for-word translation. In this paper, we address the problem of cross-cultural translation on two fronts: (i) we introduce XC-Translate, the first large-scale, manually-created benchmark for machine translation that focuses on text that contains potentially culturally-nuanced entity names, and (ii) we propose KG-MT, a novel end-to-end method to integrate information from a multilingual knowledge graph into a neural machine translation model by leveraging a dense retrieval mechanism. Our experiments and analyses show that current machine translation systems and large language models still struggle to translate texts containing entity names, whereas KG-MT outperforms state-of-the-art approaches by a large margin, obtaining a 129% and 62% relative improvement compared to NLLB-200 and GPT-4, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14057 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs Conia, Simone Lee, Daniel Li, Min Minhas, Umar Farooq Potdar, Saloni Li, Yunyao Computation and Language Artificial Intelligence Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages. These variations may also be caused by transcreation, an adaptation process that entails more than transliteration and word-for-word translation. In this paper, we address the problem of cross-cultural translation on two fronts: (i) we introduce XC-Translate, the first large-scale, manually-created benchmark for machine translation that focuses on text that contains potentially culturally-nuanced entity names, and (ii) we propose KG-MT, a novel end-to-end method to integrate information from a multilingual knowledge graph into a neural machine translation model by leveraging a dense retrieval mechanism. Our experiments and analyses show that current machine translation systems and large language models still struggle to translate texts containing entity names, whereas KG-MT outperforms state-of-the-art approaches by a large margin, obtaining a 129% and 62% relative improvement compared to NLLB-200 and GPT-4, respectively. |
| title | Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.14057 |