{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:49:37Z","timestamp":1773481777807,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936104"],"award-info":[{"award-number":["U1936104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3485447.3511957","type":"proceedings-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T05:11:23Z","timestamp":1650863483000},"page":"286-296","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval"],"prefix":"10.1145","author":[{"given":"Shitao","family":"Xiao","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}]},{"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, China"}]},{"given":"Weihao","family":"Han","sequence":"additional","affiliation":[{"name":"Microsoft Search Technology Center Asia, China"}]},{"given":"Jianjin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Search Technology Center Asia, China"}]},{"given":"Yingxia","family":"Shao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}]},{"given":"Defu","family":"Lian","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China"}]},{"given":"Chaozhuo","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, China"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"Microsoft Search Technology Center Asia, China"}]},{"given":"Denvy","family":"Deng","sequence":"additional","affiliation":[{"name":"Microsoft Search Technology Center Asia, China"}]},{"given":"Liangjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Search Technology Center Asia, China"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Search Technology Center Asia, China"}]},{"given":"Xing","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, China"}]}],"member":"320","published-online":{"date-parts":[[2022,4,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Ayaan\u00a0Kakkar and Mukesh Mohania","author":"Anirban\u00a0Mondal Nilesh\u00a0Padhariya","year":"2021","unstructured":"Nilesh\u00a0Padhariya Anirban\u00a0Mondal, Ayaan\u00a0Kakkar and Mukesh Mohania. 2021. Efficient Indexing of Top-k Entities in Systems of Engagement with Extensions for Geo-tagged Entities. Data Science and Engineering(2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_13"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609451"},{"key":"e_1_3_2_1_4_1","unstructured":"Yoshua Bengio Nicholas L\u00e9onard and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432(2013)."},{"key":"e_1_3_2_1_5_1","unstructured":"Wei-Cheng Chang Felix\u00a0X Yu Yin-Wen Chang Yiming Yang and Sanjiv Kumar. 2020. Pre-training tasks for embedding-based large-scale retrieval. arXiv preprint arXiv:2002.03932(2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR, 1597\u20131607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597\u20131607."},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning. PMLR, 1617\u20131626","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\u20131626."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Nick Craswell Bhaskar Mitra Emine Yilmaz Daniel Campos and Ellen\u00a0M Voorhees. 2020. Overview of the trec 2019 deep learning track. arXiv preprint arXiv:2003.07820(2020).","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018).","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330651"},{"key":"e_1_3_2_1_12_1","unstructured":"Cong Fu Chao Xiang Changxu Wang and Deng Cai. 2017. Fast approximate nearest neighbor search with the navigating spreading-out graph. arXiv preprint arXiv:1707.00143(2017)."},{"key":"e_1_3_2_1_13_1","unstructured":"Tianyu Gao Xingcheng Yao and Danqi Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings. arXiv preprint arXiv:2104.08821(2021)."},{"key":"e_1_3_2_1_14_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 36, 4(2013), 744\u2013755."},{"key":"e_1_3_2_1_15_1","volume-title":"Realm: Retrieval-augmented language model pre-training. arXiv preprint arXiv:2002.08909(2020).","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. Realm: Retrieval-augmented language model pre-training. arXiv preprint arXiv:2002.08909(2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_1_19_1","unstructured":"Tomoki Ito Kota Tsubouchi Hiroki Sakaji Tatsuo Yamashita and Kiyoshi Izumi. 2020. Contextual Sentiment Neural Network for Document Sentiment Analysis. Data Science and Engineering(2020)."},{"key":"e_1_3_2_1_20_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 33, 1(2010), 117\u2013128."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946540"},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.\u00a0F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Jin Binbin","year":"2020","unstructured":"Binbin Jin, Defu Lian, Zheng Liu, Qi Liu, Jianhui Ma, Xing Xie, and Enhong Chen. 2020. Sampling-Decomposable Generative Adversarial Recommender. In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.\u00a0F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., 22629\u201322639. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/ff42b03a06a1bed4e936f0e04958e168-Paper.pdf"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 1188\u20131196","author":"Le Quoc","year":"2014","unstructured":"Quoc Le and Tomas Mikolov. 2014. Distributed representations of sentences and documents. In International conference on machine learning. PMLR, 1188\u20131196."},{"key":"e_1_3_2_1_26_1","unstructured":"Kenton Lee Ming-Wei Chang and Kristina Toutanova. 2019. Latent retrieval for weakly supervised open domain question answering. arXiv preprint arXiv:1906.00300(2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380151"},{"key":"e_1_3_2_1_28_1","first-page":"1919","article-title":"Discrete matrix factorization and extension for fast item recommendation","volume":"33","author":"Lian Defu","year":"2019","unstructured":"Defu Lian, Xing Xie, and Enhong Chen. 2019. Discrete matrix factorization and extension for fast item recommendation. IEEE Transactions on Knowledge and Data Engineering 33, 5(2019), 1919\u20131933.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467149"},{"key":"e_1_3_2_1_30_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019).","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_1_31_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_1_32_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov A","year":"2018","unstructured":"Yu\u00a0A Malkov and Dmitry\u00a0A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence 42, 4(2018), 824\u2013836."},{"key":"e_1_3_2_1_33_1","volume-title":"Fast approximate nearest neighbors with automatic algorithm configuration.VISAPP (1) 2, 331-340","author":"Muja Marius","year":"2009","unstructured":"Marius Muja and David\u00a0G Lowe. 2009. Fast approximate nearest neighbors with automatic algorithm configuration.VISAPP (1) 2, 331-340 (2009), 2."},{"key":"e_1_3_2_1_34_1","unstructured":"Aaron van\u00a0den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748(2018)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_36_1","volume-title":"Hm-ann: Efficient billion-point nearest neighbor search on heterogeneous memory. Advances in Neural Information Processing Systems 33","author":"Ren Jie","year":"2020","unstructured":"Jie Ren, Minjia Zhang, and Dong Li. 2020. Hm-ann: Efficient billion-point nearest neighbor search on heterogeneous memory. Advances in Neural Information Processing Systems 33 (2020)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2577348"},{"key":"e_1_3_2_1_38_1","unstructured":"Aditi Singh Suhas\u00a0Jayaram Subramanya Ravishankar Krishnaswamy and Harsha\u00a0Vardhan Simhadri. 2021. FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Search. arXiv preprint arXiv:2105.09613(2021)."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13766\u201313776","author":"Subramanya Suhas\u00a0Jayaram","year":"2019","unstructured":"Suhas\u00a0Jayaram Subramanya, Rohan Kadekodi, Ravishankar Krishaswamy, and Harsha\u00a0Vardhan Simhadri. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13766\u201313776."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.640"},{"key":"e_1_3_2_1_41_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\u00a0N. 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_1_42_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_1_43_1","volume-title":"Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems 32","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ\u00a0R Salakhutdinov, and Quoc\u00a0V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"}],"event":{"name":"WWW '22: The ACM Web Conference 2022","location":"Virtual Event, Lyon France","acronym":"WWW '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2022"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3511957","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485447.3511957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:09Z","timestamp":1750191129000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3511957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":44,"alternative-id":["10.1145\/3485447.3511957","10.1145\/3485447"],"URL":"https:\/\/doi.org\/10.1145\/3485447.3511957","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-04-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}