mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval
Sheng-Chieh Lin, Amin Ahmad, Jimmy Lin
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.
BibTeX
@inproceedings{
lin2023maggretriever,
title={mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval},
author={Sheng-Chieh Lin and Amin Ahmad and Jimmy Lin},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=IEH9YsR5Ty}
}