DeeBERT: Dynamic early exiting for accelerating BERT inference J Xin, R Tang, J Lee, Y Yu, J Lin arXiv preprint arXiv:2004.12993, 2020 | 367 | 2020 |
BERxiT: Early exiting for BERT with better fine-tuning and extension to regression J Xin, R Tang, Y Yu, J Lin Proceedings of the 16th conference of the European chapter of the …, 2021 | 118 | 2021 |
Improving neural fine-grained entity typing with knowledge attention J Xin, Y Lin, Z Liu, M Sun Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018 | 76 | 2018 |
The art of abstention: Selective prediction and error regularization for natural language processing J Xin, R Tang, Y Yu, J Lin Proceedings of the 59th Annual Meeting of the Association for Computational …, 2021 | 59 | 2021 |
Early exiting BERT for efficient document ranking J Xin, R Nogueira, Y Yu, J Lin Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language …, 2020 | 52 | 2020 |
Zero-shot dense retrieval with momentum adversarial domain invariant representations J Xin, C Xiong, A Srinivasan, A Sharma, D Jose, PN Bennett arXiv preprint arXiv:2110.07581, 2021 | 46 | 2021 |
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 | 27 | 2021 |
Put it back: Entity typing with language model enhancement J Xin, H Zhu, X Han, Z Liu, M Sun Proceedings of the 2018 Conference on Empirical Methods in Natural Language …, 2018 | 25 | 2018 |
Approach zero and Anserini at the CLEF-2021 ARQMath track: Applying substructure search and BM25 on operator tree path tokens W Zhong, X Zhang, J Xin, R Zanibbi, J Lin Proc. CLEF 2021 (CEUR Working Notes), 2021 | 17 | 2021 |
How does BERT rerank passages? an attribution analysis with information bottlenecks Z Jiang, R Tang, J Xin, J Lin Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting …, 2021 | 13 | 2021 |
Inserting information bottlenecks for attribution in transformers Z Jiang, R Tang, J Xin, J Lin arXiv preprint arXiv:2012.13838, 2020 | 13 | 2020 |
Temporal early exiting for streaming speech commands recognition R Tang, K Kumar, J Xin, P Vyas, W Li, G Yang, Y Mao, C Murray, J Lin ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 12 | 2022 |
Few-shot non-parametric learning with deep latent variable model Z Jiang, Y Dai, J Xin, M Li, J Lin Advances in Neural Information Processing Systems 35, 26448-26461, 2022 | 11 | 2022 |
Serverless BM25 Search and BERT Reranking. M Anand, J Zhang, S Ding, J Xin, J Lin DESIRES, 3-9, 2021 | 10 | 2021 |
Certified error control of candidate set pruning for two-stage relevance ranking M Li, X Zhang, J Xin, H Zhang, J Lin arXiv preprint arXiv:2205.09638, 2022 | 8 | 2022 |
Showing Your Work Doesn't Always Work R Tang, J Lee, J Xin, X Liu, Y Yu, J Lin arXiv preprint arXiv:2004.13705, 2020 | 8 | 2020 |
What part of the neural network does this? Understanding LSTMs by measuring and dissecting neurons J Xin, J Lin, Y Yu Proceedings of the 2019 Conference on Empirical Methods in Natural Language …, 2019 | 6 | 2019 |
Bag-of-Words Baselines for Semantic Code Search X Zhang, J Xin, A Yates, J Lin Proceedings of the 1st Workshop on Natural Language Processing for …, 2021 | 4 | 2021 |
Building an efficiency pipeline: Commutativity and cumulativeness of efficiency operators for transformers J Xin, R Tang, Z Jiang, Y Yu, J Lin arXiv preprint arXiv:2208.00483, 2022 | 2 | 2022 |
Voice query auto completion R Tang, K Kumar, K Chalkley, J Xin, L Zhang, W Li, G Yang, Y Mao, J Shin, ... Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021 | 2 | 2021 |