Publications
2024
- CELI: Simple yet Effective Approach to Enhance Out-of-Domain Generalization of Cross-Encoders
Xinyu Zhang*, Minghan Li*, Jimmy Lin
North American Chapter of the Association for Computational Linguistics (NAACL), 2024 (upcoming).
Preprint abs/2302.06589, 2023.
[Paper]
2023
How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval
Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, Xilun Chen
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
[Paper] / [Code]CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval
Minghan Li*, Sheng-Chieh Lin, Barlas Oguz, Asish Ghoshal, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, Xilun Chen*
Association for Computational Linguistics (ACL), 2023.
[Paper] / [Code]SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
Minghan Li, Sheng-Chieh Lin, Xueguang Ma, Jimmy Lin
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2023.
[Paper] / [Code]Aggretriever: A Simple Approach to Aggregate Textual Representation for Robust Dense Passage Retrieval
Sheng-Chieh Lin, Minghan Li, Jimmy Lin
Transactions of the Association for Computational Linguistics (TACL), 2023.
[Paper] / [Code]
2022
Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking
Minghan Li*, Xinyu Zhang*, Ji Xin, Hongyang Zhang, Jimmy Lin
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.
[Paper] / [Code]An Encoder Attribution Analysis for Dense Passage Retriever in Open-Domain Question Answering
Minghan Li, Xueguang Ma, Jimmy Lin
The 2nd Workshop on Trustworthy Natural Language Processing (NAACL), 2022.
[Paper]
2021
Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval
Xueguang Ma*, Minghan Li*, Kai Sun, Ji Xin, Jimmy Lin
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
[Paper] / [Code]Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answering
Minghan Li*, Ming Li, Kun Xiong, Jimmy Lin
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
[Paper] / [Code]Another Look at DPR: Reproduction of Training and Replication of Retrieval
Xueguang Ma, Kai Sun, Ronak Pradeep, Minghan Li, Jimmy Lin
Conference on European Conference on Information Retrieval (ECIR), 2022.
[Paper] / [Code]