Abstract
Dense passage retrieval has been shown to be an effective approach for information retrieval tasks such as open domain question answering. Under this paradigm, a dual-encoder model is learned to encode questions and passages separately into vector representations, and all the passage vectors are then pre-computed and indexed, which can be efficiently retrieved by vector space search during inference time. In this paper, we propose a new contrastive learning method called Cross Momentum Contrastive learning (xMoCo), for learning a dual-encoder model for question-passage matching. Our method efficiently maintains a large pool of negative samples like the original MoCo, and by jointly optimizing question-to-passage and passage-to-question matching tasks, enables using separate encoders for questions and passages. We evaluate our method on various open-domain question answering dataset, and the experimental results show the effectiveness of the proposed method.- Anthology ID:
- 2021.acl-long.477
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6120–6129
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.477
- DOI:
- 10.18653/v1/2021.acl-long.477
- Cite (ACL):
- Nan Yang, Furu Wei, Binxing Jiao, Daxing Jiang, and Linjun Yang. 2021. xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6120–6129, Online. Association for Computational Linguistics.
- Cite (Informal):
- xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering (Yang et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2021.acl-long.477.pdf
- Data
- Natural Questions, SQuAD, TriviaQA, WebQuestions