关注
Minghan Li
Minghan Li
在 uwaterloo.ca 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval
SC Lin, A Asai, M Li, B Oguz, J Lin, Y Mehdad, W Yih, X Chen
Proceedings of the 46th International ACM SIGIR Conference on Research and …, 2023
502023
Simple and effective unsupervised redundancy elimination to compress dense vectors for passage retrieval
X Ma, M Li, K Sun, J Xin, J Lin
Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021
252021
Another look at DPR: reproduction of training and replication of retrieval
X Ma, K Sun, R Pradeep, M Li, J Lin
European Conference on Information Retrieval, 613-626, 2022
202022
Aggretriever: A simple approach to aggregate textual representations for robust dense passage retrieval
SC Lin, M Li, J Lin
Transactions of the Association for Computational Linguistics 11, 436-452, 2023
192023
CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval
M Li, SC Lin, B Oguz, A Ghoshal, J Lin, Y Mehdad, W Yih, X Chen
Proceedings of the 61st Annual Meeting of the Association for Computational …, 2022
192022
SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
M Li, SC Lin, X Ma, J Lin
Proceedings of the 46th International ACM SIGIR Conference on Research and …, 2023
152023
Multi-task dense retrieval via model uncertainty fusion for open-domain question answering
M Li, M Li, K Xiong, J Lin
Findings of the Association for Computational Linguistics: EMNLP 2021, 274-287, 2021
122021
Query expansion using contextual clue sampling with language models
L Liu, M Li, J Lin, S Riedel, P Stenetorp
arXiv preprint arXiv:2210.07093, 2022
102022
Encoder adaptation of dense passage retrieval for open-domain question answering
M Li, J Lin
arXiv preprint arXiv:2110.01599, 2021
82021
Certified error control of candidate set pruning for two-stage relevance ranking
M Li, X Zhang, J Xin, H Zhang, J Lin
Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022
62022
An encoder attribution analysis for dense passage retriever in open-domain question answering
M Li, X Ma, J Lin
Proceedings of the 2nd Workshop on Trustworthy Natural Language Processing …, 2022
62022
Generate, filter, and fuse: Query expansion via multi-step keyword generation for zero-shot neural rankers
M Li, H Zhuang, K Hui, Z Qin, J Lin, R Jagerman, X Wang, M Bendersky
arXiv preprint arXiv:2311.09175, 2023
42023
Accelerating large scale knowledge distillation via dynamic importance sampling
M Li, T Zuo, R Li, M White, W Zheng
arXiv preprint arXiv:1812.00914, 2018
32018
Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction
X Zhang, M Li, J Lin
arXiv preprint arXiv:2302.06589, 2023
12023
Latte-Mix: Measuring Sentence Semantic Similarity with Latent Categorical Mixtures
M Li, H Bai, L Tan, K Xiong, J Lin
arXiv preprint arXiv:2010.11351, 2020
12020
CELI: Simple yet Effective Approach to Enhance Out-of-Domain Generalization of Cross-Encoders.
C Zhang, M Li, J Lin
Proceedings of the 2024 Conference of the North American Chapter of the …, 2024
2024
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
M Li, X Chen, A Holtzman, B Chen, J Lin, W Yih, XV Lin
arXiv preprint arXiv:2405.19325, 2024
2024
系统目前无法执行此操作,请稍后再试。
文章 1–17