Abstract
Multilingual information retrieval (MLIR) is a crucial yet challenging task due to the need for human annotations in multiple languages, making training data creation labor-intensive. In this paper, we introduce mAggretriever, which effectively leverages semantic and lexical features from pre-trained multilingual transformers (e.g., mBERT and XLM-R) for dense retrieval. To enhance training and inference efficiency, we employ approximate masked-language modeling prediction for computing lexical features, reducing 70–85% GPU memory requirement for mAggretriever fine-tuning. Empirical results demonstrate that mAggretriever, fine-tuned solely on English training data, surpasses existing state-of-the-art multilingual dense retrieval models that undergo further training on large-scale MLIR training data. Our code is available at url.- Anthology ID:
- 2023.emnlp-main.715
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11688–11696
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.715
- DOI:
- 10.18653/v1/2023.emnlp-main.715
- Cite (ACL):
- Sheng-Chieh Lin, Amin Ahmad, and Jimmy Lin. 2023. mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11688–11696, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval (Lin et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.emnlp-main.715.pdf