{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:19:41Z","timestamp":1784179181066,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462891","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T02:41:48Z","timestamp":1626057708000},"page":"113-122","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":204,"title":["Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling"],"prefix":"10.1145","author":[{"given":"Sebastian","family":"Hofst\u00e4tter","sequence":"first","affiliation":[{"name":"TU Wien, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng-Chieh","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jheng-Hong","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allan","family":"Hanbury","sequence":"additional","affiliation":[{"name":"TU Wien, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proc. of EMNLP-IJCNLP .","author":"Yilmaz Zeynep Akkalyoncu","year":"2019","unstructured":"Zeynep Akkalyoncu Yilmaz, Wei Yang, Haotian Zhang, and Jimmy Lin. 2019. Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval. In Proc. of EMNLP-IJCNLP ."},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. of NIPS .","author":"Bajaj Payal","year":"2016","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, and Tri Nguyen. 2016. MS MARCO : A Human Generated MAchine Reading COmprehension Dataset. In Proc. of NIPS ."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"e_1_3_2_1_4_1","volume-title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments. arXiv:2006.09882","author":"Caron Mathilde","year":"2021","unstructured":"Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, and Armand Joulin. 2021. Unsupervised Learning of Visual Features by Contrasting Cluster Assignments. arXiv:2006.09882 (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"Simplified TinyBERT: Knowledge Distillation for Document Retrieval. arXiv:2009.07531","author":"Chen Xuanang","year":"2020","unstructured":"Xuanang Chen, Ben He, Kai Hui, Le Sun, and Yingfei Sun. 2020. Simplified TinyBERT: Knowledge Distillation for Document Retrieval. arXiv:2009.07531 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. of ICTIR .","author":"Cohen Daniel","unstructured":"Daniel Cohen, Scott M. Jordan, and W. Bruce Croft. 2019. Learning a Better Negative Sampling Policy with Deep Neural Networks for Search. In Proc. of ICTIR ."},{"key":"e_1_3_2_1_7_1","volume-title":"Overview of the TREC 2019 Deep Learning Track. In TREC .","author":"Craswell Nick","year":"2019","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, and Daniel Campos. 2019. Overview of the TREC 2019 Deep Learning Track. In TREC ."},{"key":"e_1_3_2_1_8_1","volume-title":"Overview of the TREC 2020 Deep Learning Track. In TREC .","author":"Craswell Nick","year":"2020","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, and Daniel Campos. 2020. Overview of the TREC 2020 Deep Learning Track. In TREC ."},{"key":"e_1_3_2_1_9_1","volume-title":"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:1910.10687 (2019)."},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. of NAACL .","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 Proc. of NAACL ."},{"key":"e_1_3_2_1_11_1","volume-title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering. arXiv:2010.08191","author":"Yuchen Ding Yingqi Qu","year":"2020","unstructured":"Yingqi Qu Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2020. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering. arXiv:2010.08191 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"Understanding BERT Rankers Under Distillation. arXiv:2007.11088","author":"Gao Luyu","year":"2020","unstructured":"Luyu Gao, Zhuyun Dai, and Jamie Callan. 2020. Understanding BERT Rankers Under Distillation. arXiv:2007.11088 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline. arXiv:2101.08751","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao, Zhuyun Dai, and Jamie Callan. 2021. Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline. arXiv:2101.08751 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. arXiv:2010.02666","author":"Sebastian","year":"2020","unstructured":"Sebastian Hofst\"atter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. arXiv:2010.02666 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. of OSIRRC .","author":"Allan Hanbury Sebastian","year":"2019","unstructured":"Sebastian Hofst\"atter and Allan Hanbury. 2019. Let's Measure Run Time! Extending the IR Replicability Infrastructure to Include Performance Aspects. In Proc. of OSIRRC ."},{"key":"e_1_3_2_1_16_1","volume-title":"Distilling Knowledge from Reader to Retriever for Question Answering. 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:2012.04584 (2020)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0271(71)90051-9"},{"key":"e_1_3_2_1_18_1","volume-title":"TinyBERT: Distilling BERT for Natural Language Understanding. 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:1909.10351 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Billion-Scale Similarity Search with GPUs . arXiv:1702.08734","author":"Johnson Jeff","year":"2017","unstructured":"Jeff Johnson, Matthijs Douze, and Herv\u00e9 J\u00e9gou. 2017. Billion-Scale Similarity Search with GPUs . arXiv:1702.08734 (2017)."},{"key":"e_1_3_2_1_20_1","volume-title":"Noe Pion, Philippe Weinzaepfel, and Diane Larlus.","author":"Kalantidis Yannis","year":"2020","unstructured":"Yannis Kalantidis, Mert Bulent Sariyildiz, Noe Pion, Philippe Weinzaepfel, and Diane Larlus. 2020. Hard Negative Mixing for Contrastive Learning. Advances in Neural Information Processing Systems , Vol. 33 (2020)."},{"key":"e_1_3_2_1_21_1","volume-title":"Dense Passage Retrieval for Open-Domain Question Answering. arXiv:2004.04906","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_23_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_24_1","volume-title":"Distilling Dense Representations for Ranking using Tightly-Coupled Teachers. 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:2010.11386 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrieval. arXiv:2002.06275","author":"Lu Wenhao","year":"2020","unstructured":"Wenhao Lu, Jian Jiao, and Ruofei Zhang. 2020. TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrieval. arXiv:2002.06275 (2020)."},{"key":"e_1_3_2_1_26_1","volume-title":"arXiv:2005.00181","author":"Luan Yi","year":"2020","unstructured":"Yi Luan, Jacob Eisenstein, Kristina Toutanova, and Michael Collins. 2020. Sparse, Dense, and Attentional Representations for Text Retrieval. arXiv:2005.00181 (2020)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401094"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331317"},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of the Fifth Berkeley Symposium on Mathematical Statistics and Probability","volume":"1","author":"MacQueen James","year":"1967","unstructured":"James MacQueen. 1967. Some Methods for Classification and Analysis of Multivariate observations. In Proc. of the Fifth Berkeley Symposium on Mathematical Statistics and Probability , Vol. 1. 281--297."},{"key":"e_1_3_2_1_30_1","volume-title":"Passage Re-ranking with BERT. arXiv:1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_1_31_1","volume-title":"From doc2query to docTTTTTquery. Online preprint","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Jimmy Lin. 2019. From doc2query to docTTTTTquery. Online preprint (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"Proc. of NIPS-W .","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic Differentiation in PyTorch. In Proc. of NIPS-W ."},{"key":"e_1_3_2_1_33_1","volume-title":"The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models. arXiv:2101.05667","author":"Pradeep Ronak","year":"2021","unstructured":"Ronak Pradeep, Rodrigo Nogueira, and Jimmy Lin. 2021. The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models. arXiv:2101.05667 (2021)."},{"key":"e_1_3_2_1_34_1","volume-title":"Faster, Cheaper and Lighter. 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:1910.01108 (2019)."},{"key":"e_1_3_2_1_35_1","volume-title":"Rethinking Image Mixture for Unsupervised Visual Representation Learning. arXiv:2003.05438","author":"Shen Zhiqiang","year":"2020","unstructured":"Zhiqiang Shen, Zechun Liu, Zhuang Liu, Marios Savvides, and Trevor Darrell. 2020. Rethinking Image Mixture for Unsupervised Visual Representation Learning. arXiv:2003.05438 (2020)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220021"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401296"},{"key":"e_1_3_2_1_38_1","volume-title":"Proc. of NIPS .","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Proc. of NIPS ."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/253495.253524"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271784"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_42_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. 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:2007.00808 (2020)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080721"},{"key":"e_1_3_2_1_44_1","volume-title":"Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently. arXiv:2010.10469","author":"Zhan Jingtao","year":"2020","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang, and Shaoping Ma. 2020. Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently. arXiv:2010.10469 (2020)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291014"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462891","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462891","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:18Z","timestamp":1750193238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462891"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":45,"alternative-id":["10.1145\/3404835.3462891","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462891","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}