Cross-Lingual Phrase Retrieval
Heqi Zheng, Xiao Zhang, Zewen Chi, Heyan Huang, Yan Tan, Tian Lan, Wei Wei, Xian-Ling Mao
Abstract
Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representations in word or sentence level. However, how to learn phrase representations for cross-lingual phrase retrieval is still an open problem. In this paper, we propose , a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences. Moreover, we create a large-scale cross-lingual phrase retrieval dataset, which contains 65K bilingual phrase pairs and 4.2M example sentences in 8 English-centric language pairs. Experimental results show that outperforms state-of-the-art baselines which utilize word-level or sentence-level representations. also shows impressive zero-shot transferability that enables the model to perform retrieval in an unseen language pair during training. Our dataset, code, and trained models are publicly available at github.com/cwszz/XPR/.- Anthology ID:
- 2022.acl-long.288
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4193–4204
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.288
- DOI:
- 10.18653/v1/2022.acl-long.288
- Cite (ACL):
- Heqi Zheng, Xiao Zhang, Zewen Chi, Heyan Huang, Yan Tan, Tian Lan, Wei Wei, and Xian-Ling Mao. 2022. Cross-Lingual Phrase Retrieval. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4193–4204, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Lingual Phrase Retrieval (Zheng et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.acl-long.288.pdf
- Code
- cwszz/xpr