{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:04:11Z","timestamp":1784178251936,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210104043"],"award-info":[{"award-number":["DP210104043"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591915","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"2542-2551","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Balanced Topic Aware Sampling for Effective Dense Retriever: A Reproducibility Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0726-5250","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0271-5563","authenticated-orcid":false,"given":"Guido","family":"Zuccon","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_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_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2102.07662"},{"key":"e_1_3_2_1_3_1","volume-title":"Overview of the TREC 2019 deep learning track. arXiv preprint arXiv:2003","author":"Craswell Nick","year":"2020","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, and Ellen M Voorhees. 2020. Overview of the TREC 2019 deep learning track. arXiv preprint arXiv:2003.07820 (2020)."},{"key":"e_1_3_2_1_4_1","volume-title":"Condenser: a pre-training architecture for dense retrieval. arXiv preprint arXiv:2104.08253","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao and Jamie Callan. 2021. Condenser: a pre-training architecture for dense retrieval. arXiv preprint arXiv:2104.08253 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_6_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_7_1","volume-title":"Improving efficient neural ranking models with cross-architecture knowledge distillation. arXiv preprint arXiv:2010.02666","author":"Hofst\u00e4tter Sebastian","year":"2020","unstructured":"Sebastian Hofst\u00e4tter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020. Improving efficient neural ranking models with cross-architecture knowledge distillation. arXiv preprint arXiv:2010.02666 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_9_1","volume-title":"Distilling knowledge from reader to retriever for question answering. arXiv preprint arXiv:2012.04584","author":"Izacard Gautier","year":"2020","unstructured":"Gautier Izacard and Edouard Grave. 2020. Distilling knowledge from reader to retriever for question answering. arXiv preprint arXiv:2012.04584 (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"Tinybert: Distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351","author":"Jiao Xiaoqi","year":"2019","unstructured":"Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, and Qun Liu. 2019. Tinybert: Distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531884"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_13_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_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401083"},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. 5th Berkeley Symposium on Math., Stat., and Prob. 281","author":"MacQueen J","year":"1965","unstructured":"J MacQueen. 1965. Some methods for classification and analysis of multivariate observations. In Proc. 5th Berkeley Symposium on Math., Stat., and Prob. 281."},{"key":"e_1_3_2_1_16_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. choice","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. choice, Vol. 2640 (2016), 660."},{"key":"e_1_3_2_1_17_1","volume-title":"Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Lin. 2019. Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424 (2019)."},{"key":"e_1_3_2_1_18_1","unstructured":"Chandan K. Reddy Llu\u00eds M\u00e0rquez Fran Valero Nikhil Rao Hugo Zaragoza Sambaran Bandyopadhyay Arnab Biswas Anlu Xing and Karthik Subbian. 2022. Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search. (2022). arxiv: 2206.06588"},{"key":"e_1_3_2_1_19_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Lecture Notes on Neural Information Retrieval. arXiv preprint arXiv:2207.13443","author":"Tonellotto Nicola","year":"2022","unstructured":"Nicola Tonellotto. 2022. Lecture Notes on Neural Information Retrieval. arXiv preprint arXiv:2207.13443 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3471158.3472233"},{"key":"e_1_3_2_1_22_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_23_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_1_24_1","volume-title":"Dense text retrieval based on pretrained language models: A survey. arXiv preprint arXiv:2211.14876","author":"Zhao Wayne Xin","year":"2022","unstructured":"Wayne Xin Zhao, Jing Liu, Ruiyang Ren, and Ji-Rong Wen. 2022. Dense text retrieval based on pretrained language models: A survey. arXiv preprint arXiv:2211.14876 (2022)."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591915","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:07Z","timestamp":1750178287000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591915"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":24,"alternative-id":["10.1145\/3539618.3591915","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591915","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}