{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T13:48:23Z","timestamp":1770040103471,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T00:00:00Z","timestamp":1691539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation","award":["2225942"],"award-info":[{"award-number":["2225942"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,9]]},"DOI":"10.1145\/3578337.3605120","type":"proceedings-article","created":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T22:12:46Z","timestamp":1691619166000},"page":"247-255","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Balanced Knowledge Distillation with Contrastive Learning for Document Re-ranking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6454-5796","authenticated-orcid":false,"given":"Yingrui","family":"Yang","sequence":"first","affiliation":[{"name":"UCSB, Santa Barbara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8581-6733","authenticated-orcid":false,"given":"Shanxiu","family":"He","sequence":"additional","affiliation":[{"name":"UCSB, Santa Barbara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5717-2637","authenticated-orcid":false,"given":"Yifan","family":"Qiao","sequence":"additional","affiliation":[{"name":"UCSB, Santa Barbara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7870-3100","authenticated-orcid":false,"given":"Wentai","family":"Xie","sequence":"additional","affiliation":[{"name":"UCSB, Santa Barbara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1902-3387","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[{"name":"UCSB, Santa Barbara, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,8,9]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. ArXiv","author":"Campos Daniel Fernando","year":"2016","unstructured":"Daniel Fernando Campos, Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, Li Deng, and Bhaskar Mitra. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. ArXiv, Vol. abs\/1611.09268 (2016)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"e_1_3_2_2_3_1","volume-title":"Simplified TinyBERT: Knowledge Distillation for Document Retrieval. ArXiv","author":"Chen Xuanang","year":"2020","unstructured":"Xuanang Chen, B. He, Kai Hui, L. Sun, and Yingfei Sun. 2020. Simplified TinyBERT: Knowledge Distillation for Document Retrieval. ArXiv, Vol. abs\/2009.07531 (2020)."},{"key":"e_1_3_2_2_4_1","unstructured":"Co-Condenser. 2021. https:\/\/huggingface.co\/Luyu\/co-condenser-marco. (2021)."},{"key":"e_1_3_2_2_5_1","volume-title":"Overview of the TREC 2020 Deep Learning Track. ArXiv","volume":"2102","author":"Craswell Nick","year":"2020","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Fernando Campos, and Ellen M. Voorhees. 2020. Overview of the TREC 2020 Deep Learning Track. ArXiv, Vol. abs\/2102.07662 (2020)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Zhuyun Dai and J. Callan. 2019. Deeper Text Understanding for IR with Contextual Neural Language Modeling. SIGIR (2019).","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_2_7_1","volume-title":"Context-Aware Term Weighting For First Stage Passage Retrieval. SIGIR","author":"Dai Zhuyun","year":"2020","unstructured":"Zhuyun Dai and Jamie Callan. 2020. Context-Aware Term Weighting For First Stage Passage Retrieval. SIGIR (2020)."},{"key":"e_1_3_2_2_8_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT.","author":"Devlin J.","year":"2019","unstructured":"J. Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT."},{"key":"e_1_3_2_2_9_1","volume-title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. ArXiv","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, C. Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021a. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. ArXiv, Vol. abs\/2109.10086 (2021)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531857"},{"key":"e_1_3_2_2_11_1","volume-title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. SIGIR","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021b. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. SIGIR (2021)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of SIGIR","author":"Gao Luyu","year":"2020","unstructured":"Luyu Gao, Zhuyun Dai, and J. Callan. 2020. Understanding BERT Rankers Under Distillation. Proceedings of SIGIR (2020)."},{"key":"e_1_3_2_2_14_1","volume-title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List. NAACL","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao, Zhuyun Dai, and Jamie Callan. 2021. COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List. NAACL (2021)."},{"key":"e_1_3_2_2_15_1","unstructured":"MS-MARCO Hard-Negatives. 2022. https:\/\/huggingface.co\/datasets\/sentence-transformers\/msmarco-hard-negatives. (2022)."},{"key":"e_1_3_2_2_16_1","volume-title":"Distilling the Knowledge in a Neural Network. ArXiv","author":"Hinton Geoffrey E.","year":"2015","unstructured":"Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. ArXiv, Vol. abs\/1503.02531 (2015)."},{"key":"e_1_3_2_2_17_1","volume-title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. ArXiv","author":"Sebastian","year":"2020","unstructured":"Sebastian Hofst\"atter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020a. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. ArXiv, Vol. abs\/2010.02666 (2020)."},{"key":"e_1_3_2_2_18_1","volume-title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling. SIGIR","author":"Sebastian","year":"2021","unstructured":"Sebastian Hofst\"atter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy J. Lin, and Allan Hanbury. 2021. Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling. SIGIR (2021)."},{"key":"e_1_3_2_2_19_1","unstructured":"Sebastian Hofst\"atter Markus Zlabinger and A. Hanbury. 2020b. Interpretable & Time-Budget-Constrained Contextualization for Re-Ranking. In ECAI."},{"key":"e_1_3_2_2_20_1","volume-title":"ACM Transactions on Information Systems (TOIS)","volume":"20","author":"Jaana Kalervo","year":"2002","unstructured":"Kalervo J\"arvelin and Jaana Kek\"al\"ainen. 2002. Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS), Vol. 20, 4 (2002), 422--446."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_22_1","volume-title":"Zaharia","author":"Khattab O.","year":"2020","unstructured":"O. Khattab and Matei A. Zaharia. 2020. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. SIGIR (2020)."},{"key":"e_1_3_2_2_23_1","volume-title":"An Efficiency Study for SPLADE Models. SIGIR","author":"Lassance Carlos","year":"2022","unstructured":"Carlos Lassance and St\u00e9phane Clinchant. 2022. An Efficiency Study for SPLADE Models. SIGIR (2022)."},{"key":"e_1_3_2_2_24_1","volume-title":"Wen tau Yih, and Sebastian Riedel","author":"Lewis Patrick","year":"2022","unstructured":"Patrick Lewis, Barlas O?uz, Wenhan Xiong, Fabio Petroni, Wen tau Yih, and Sebastian Riedel. 2022. Boosted Dense Retriever. NAACL (2022)."},{"key":"e_1_3_2_2_25_1","volume-title":"SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes. In SIGIR. showeprint[arxiv and sigir 2023]2302.06587 [cs.IR]","author":"Li Minghan","year":"2023","unstructured":"Minghan Li, Sheng-Chieh Lin, Xueguang Ma, and Jimmy Lin. 2023. SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes. In SIGIR. showeprint[arxiv and sigir 2023]2302.06587 [cs.IR]"},{"key":"e_1_3_2_2_26_1","volume-title":"Wen tau Yih, and Xilun Chen","author":"Li Minghan","year":"2022","unstructured":"Minghan Li, Sheng-Chieh Lin, Barlas Oguz, Asish Ghoshal, Jimmy Lin, Yashar Mehdad, Wen tau Yih, and Xilun Chen. 2022. CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval. arXiv 2211.01267 (2022). arxiv: 2211.10411 [cs.IR]"},{"key":"e_1_3_2_2_27_1","unstructured":"Jimmy Lin Rodrigo Nogueira and A. Yates. 2020. Pretrained Transformers for Text Ranking: BERT and Beyond. ArXiv Vol. abs\/2010.06467 (2020)."},{"key":"e_1_3_2_2_28_1","volume-title":"Lin and Xueguang Ma","author":"Jimmy","year":"2021","unstructured":"Jimmy J. Lin and Xueguang Ma. 2021. A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques. ArXiv, Vol. abs\/2106.14807 (2021)."},{"key":"e_1_3_2_2_29_1","volume-title":"Lin","author":"Lin Sheng-Chieh","year":"2021","unstructured":"Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy J. Lin. 2021. In-Batch Negatives for Knowledge Distillation with Tightly-Coupled Teachers for Dense Retrieval. In REPL4NLP."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Yi Luan Jacob Eisenstein Kristina Toutanova and M. Collins. 2021. Sparse Dense and Attentional Representations for Text Retrieval. TACL (2021).","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331317"},{"key":"e_1_3_2_2_32_1","volume-title":"Learning Passage Impacts for Inverted Indexes. SIGIR","author":"Mallia Antonio","year":"2021","unstructured":"Antonio Mallia, O. Khattab, Nicola Tonellotto, and Torsten Suel. 2021. Learning Passage Impacts for Inverted Indexes. SIGIR (2021)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Antonio Mallia Joel Mackenzie Torsten Suel and Nicola Tonellotto. 2022. Faster Learned Sparse Retrieval with Guided Traversal. In SIGIR. 1901--1905.","DOI":"10.1145\/3477495.3531774"},{"key":"e_1_3_2_2_34_1","unstructured":"MiniLM-L-6-v2. 2022. https:\/\/huggingface.co\/cross-encoder\/ms-marco-MiniLM-L-6-v2. (2022)."},{"key":"e_1_3_2_2_35_1","volume-title":"Conformer-Kernel with Query Term Independence for Document Retrieval. SIGIR","author":"Mitra Bhaskar","year":"2021","unstructured":"Bhaskar Mitra, Sebastian Hofst\"atter, Hamed Zamani, and Nick Craswell. 2021. Conformer-Kernel with Query Term Independence for Document Retrieval. SIGIR (2021)."},{"key":"e_1_3_2_2_36_1","volume-title":"Document Expansion by Query Prediction. ArXiv","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Jimmy J. Lin, and Kyunghyun Cho. 2019. Document Expansion by Query Prediction. ArXiv, Vol. abs\/1904.08375 (2019)."},{"key":"e_1_3_2_2_37_1","volume-title":"Zhuyun Dai, Siddhartha Brahma, Iftekhar Naim, Tao Lei, and Vincent Y. Zhao.","author":"Qian Yujie","year":"2022","unstructured":"Yujie Qian, Jinhyuk Lee, Sai Meher Karthik Duddu, Zhuyun Dai, Siddhartha Brahma, Iftekhar Naim, Tao Lei, and Vincent Y. Zhao. 2022. Multi-Vector Retrieval as Sparse Alignment. arXiv 2211.01267 (2022). arxiv: 2211.01267 [cs.CL]"},{"key":"e_1_3_2_2_38_1","volume-title":"Optimizing Guided Traversal for Fast Learned Sparse Retrieval. In ACM Web Conference (WWW '23)","author":"Qiao Yifan","year":"2023","unstructured":"Yifan Qiao, Yingrui Yang, Haixin Lin, and Tao Yang. 2023. Optimizing Guided Traversal for Fast Learned Sparse Retrieval. In ACM Web Conference (WWW '23). ACM, Austin, TX, USA."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_2_41_1","volume-title":"NAACL'22","volume":"2112","author":"Santhanam Keshav","year":"2022","unstructured":"Keshav Santhanam, O. Khattab, Jon Saad-Falcon, Christopher Potts, and Matei A. Zaharia. 2022. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. NAACL'22, Vol. ArXiv abs\/2112.01488 (2022)."},{"key":"e_1_3_2_2_42_1","volume-title":"UnifieR: A Unified Retriever for Large-Scale Retrieval. ArXiv","author":"Shen Tao","year":"2022","unstructured":"Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Kai Zhang, and Daxin Jiang. 2022. UnifieR: A Unified Retriever for Large-Scale Retrieval. ArXiv, Vol. abs\/2205.11194 (2022)."},{"key":"e_1_3_2_2_43_1","unstructured":"Wenxian Shi Yuxuan Song Hao Zhou Bohan Li and Lei Li. 2021. Follow Your Path: a Progressive Method for Knowledge Distillation. In ECML\/PKDD."},{"key":"e_1_3_2_2_44_1","volume-title":"SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval. ACL","author":"Wang Liang","year":"2023","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2023. SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval. ACL (2023)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531799"},{"key":"e_1_3_2_2_46_1","volume-title":"RetroMAE: Pre-training Retrieval-oriented Transformers via Masked Auto-Encoder. EMNLP","author":"Xiao Shitao","year":"2022","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, and Zhao Cao. 2022b. RetroMAE: Pre-training Retrieval-oriented Transformers via Masked Auto-Encoder. EMNLP (2022)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"J. Xin Rodrigo Nogueira Y. Yu and Jimmy Lin. 2020. Early Exiting BERT for Efficient Document Ranking. In SUSTAINLP.","DOI":"10.18653\/v1\/2020.sustainlp-1.11"},{"key":"e_1_3_2_2_48_1","unstructured":"Lee Xiong Chenyan Xiong Ye Li Kwok-Fung Tang Jialin Liu Paul N. Bennett Junaid Ahmed and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In ICLR."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Yingrui Yang Yifan Qiao and Tao Yang. 2022. Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking. In ACL.","DOI":"10.18653\/v1\/2022.acl-long.51"},{"key":"e_1_3_2_2_50_1","volume-title":"Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance. CIKM","author":"Zhan Jingtao","year":"2021","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021a. Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance. CIKM (2021)."},{"key":"e_1_3_2_2_51_1","volume-title":"Optimizing Dense Retrieval Model Training with Hard Negatives. CoRR","author":"Zhan Jingtao","year":"2021","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021b. Optimizing Dense Retrieval Model Training with Hard Negatives. CoRR, Vol. abs\/2104.08051 (2021). https:\/\/arxiv.org\/abs\/2104.08051"},{"key":"e_1_3_2_2_52_1","volume-title":"Adversarial Retriever-Ranker for dense text retrieval. ICLR","author":"Zhang Hang","year":"2022","unstructured":"Hang Zhang, Yeyun Gong, Yelong Shen, Jiancheng Lv, Nan Duan, and Weizhu Chen. 2022. Adversarial Retriever-Ranker for dense text retrieval. ICLR (2022)."},{"key":"e_1_3_2_2_53_1","unstructured":"Wangchunshu Zhou Canwen Xu and Julian McAuley. 2021. BERT Learns to Teach: Knowledge Distillation with Meta Learning. In ACL."}],"event":{"name":"ICTIR '23: The 2023 ACM SIGIR International Conference on the Theory of Information Retrieval","location":"Taipei Taiwan","acronym":"ICTIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578337.3605120","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578337.3605120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:04Z","timestamp":1750178824000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578337.3605120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,9]]},"references-count":53,"alternative-id":["10.1145\/3578337.3605120","10.1145\/3578337"],"URL":"https:\/\/doi.org\/10.1145\/3578337.3605120","relation":{},"subject":[],"published":{"date-parts":[[2023,8,9]]},"assertion":[{"value":"2023-08-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}