{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T19:34:56Z","timestamp":1778700896796,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of China","award":["Grant No. 61732008, 61532011, 61902209, U2001212"],"award-info":[{"award-number":["Grant No. 61732008, 61532011, 61902209, U2001212"]}]},{"name":"Beijing Academy of Artificial Intelligence (BAAI)"},{"name":"Intelligent Social Governance Platform, Major Innovation & Planning Interdisciplinary Platform for the Double-First Class Initiative, Renmin University of China"},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFC0831700"],"award-info":[{"award-number":["2018YFC0831700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University Guoqiang Research Institute"},{"name":"Beijing Outstanding Young Scientist Program","award":["NO. BJJWZYJH012019100020098"],"award-info":[{"award-number":["NO. BJJWZYJH012019100020098"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,11]]},"DOI":"10.1145\/3488560.3498443","type":"proceedings-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T21:42:57Z","timestamp":1644961377000},"page":"1328-1336","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval"],"prefix":"10.1145","author":[{"given":"Jingtao","family":"Zhan","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxin","family":"Mao","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoping","family":"Ma","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Payal Bajaj Daniel Campos Nick Craswell Li Deng Jianfeng Gao Xiaodong Liu Rangan Majumder Andrew McNamara Bhaskar Mitra Tri Nguyen et al. 2016. Ms marco: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_2_2_1","unstructured":"Leon Bottou and Yoshua Bengio. 1995. Convergence properties of the k-means algorithms. In Advances in neural information processing systems. 585--592."},{"key":"e_1_3_2_2_3_1","first-page":"23","article-title":"From ranknet to lambdarank to lambdamart: An overview","volume":"11","author":"Burges Christopher JC","year":"2010","unstructured":"Christopher JC Burges. 2010. From ranknet to lambdarank to lambdamart: An overview. Learning , Vol. 11, 23--581 (2010), 81.","journal-title":"Learning"},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Machine Learning. PMLR, 1617--1626","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Lala Li, and Yizhou Sun. 2020. Differentiable product quantization for end-to-end embedding compression. In International Conference on Machine Learning. PMLR, 1617--1626."},{"key":"e_1_3_2_2_5_1","volume-title":"Overview of the TREC 2019 deep learning track. In Text REtrieval Conference (TREC) . TREC.","author":"Craswell Nick","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, and Ellen M. Voorhees. 2020. Overview of the TREC 2019 deep learning track. In Text REtrieval Conference (TREC) . TREC."},{"key":"e_1_3_2_2_6_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems , Vol. 26 (2013), 2292--2300."},{"key":"e_1_3_2_2_7_1","volume-title":"Context-aware sentence\/passage term importance estimation for first stage retrieval. arXiv preprint arXiv:1910.10687","author":"Dai Zhuyun","year":"2019","unstructured":"Zhuyun Dai and Jamie Callan. 2019. Context-aware sentence\/passage term importance estimation for first stage retrieval. arXiv preprint arXiv:1910.10687 (2019)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380258"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.241"},{"key":"e_1_3_2_2_11_1","volume-title":"Optimized product quantization","author":"Ge Tiezheng","year":"2013","unstructured":"Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2013. Optimized product quantization. IEEE transactions on pattern analysis and machine intelligence , Vol. 36, 4 (2013), 744--755."},{"key":"e_1_3_2_2_12_1","volume-title":"Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval","author":"Gong Yunchao","year":"2012","unstructured":"Yunchao Gong, Svetlana Lazebnik, Albert Gordo, and Florent Perronnin. 2012. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE transactions on pattern analysis and machine intelligence , Vol. 35, 12 (2012), 2916--2929."},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Machine Learning. PMLR, 3887--3896","author":"Guo Ruiqi","year":"2020","unstructured":"Ruiqi Guo, Philip Sun, Erik Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar. 2020. Accelerating large-scale inference with anisotropic vector quantization. In International Conference on Machine Learning. PMLR, 3887--3896."},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '21)","author":"Sebastian","year":"2021","unstructured":"Sebastian Hofst\"atter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '21). 113--122."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_2_2_17_1","volume-title":"Product quantization for nearest neighbor search","author":"Jegou Herve","year":"2010","unstructured":"Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence , Vol. 33, 1 (2010), 117--128."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_2_21_1","volume-title":"COIL, and a Conceptual Framework for Information Retrieval Techniques. arXiv preprint arXiv:2106.14807","author":"Lin Jimmy","year":"2021","unstructured":"Jimmy Lin and Xueguang Ma. 2021. A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques. arXiv preprint arXiv:2106.14807 (2021)."},{"key":"e_1_3_2_2_22_1","volume-title":"Distilling Dense Representations for Ranking using Tightly-Coupled Teachers. arXiv preprint arXiv:2010.11386","author":"Lin Sheng-Chieh","year":"2020","unstructured":"Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy Lin. 2020. Distilling Dense Representations for Ranking using Tightly-Coupled Teachers. arXiv preprint arXiv:2010.11386 (2020)."},{"key":"e_1_3_2_2_23_1","volume-title":"RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_24_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_25_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Yu A","year":"2018","unstructured":"Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence , Vol. 42, 4 (2018), 824--836."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463030"},{"key":"e_1_3_2_2_27_1","volume-title":"2019 a. From doc2query to docTTTTTquery. Online preprint","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Jimmy Lin, and AI Epistemic. 2019 a. From doc2query to docTTTTTquery. Online preprint (2019)."},{"key":"e_1_3_2_2_28_1","volume-title":"2019 b. Document expansion by query prediction. arXiv preprint arXiv:1904.08375","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Jimmy Lin, and Kyunghyun Cho. 2019 b. Document expansion by query prediction. arXiv preprint arXiv:1904.08375 (2019)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_24"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772862"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz et al. 2019. HuggingFace's Transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019).","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_2_33_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=zeFrfgyZln","author":"Xiong Lee","year":"2021","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 International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Ikuya Yamada Akari Asai and Hannaneh Hajishirzi. 2021. Efficient Passage Retrieval with Hashing for Open-domain Question Answering. In ACL .","DOI":"10.18653\/v1\/2021.acl-short.123"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482358"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"},{"key":"e_1_3_2_2_37_1","volume-title":"RepBERT: Contextualized Text Embeddings for First-Stage Retrieval. arXiv preprint arXiv:2006.15498","author":"Zhan Jingtao","year":"2020","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang, and Shaoping Ma. 2020. RepBERT: Contextualized Text Embeddings for First-Stage Retrieval. arXiv preprint arXiv:2006.15498 (2020)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462988"}],"event":{"name":"WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining","location":"Virtual Event AZ USA","acronym":"WSDM '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498443","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488560.3498443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:18Z","timestamp":1750188678000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,11]]},"references-count":38,"alternative-id":["10.1145\/3488560.3498443","10.1145\/3488560"],"URL":"https:\/\/doi.org\/10.1145\/3488560.3498443","relation":{},"subject":[],"published":{"date-parts":[[2022,2,11]]},"assertion":[{"value":"2022-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}