{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T03:00:21Z","timestamp":1784775621010,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":43,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Waterloo-Huawei Joint Innovation Laboratory"},{"DOI":"10.13039\/501100010785","name":"Canada First Research Excellence Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3463238","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T03:08:41Z","timestamp":1626059321000},"page":"2356-2362","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":277,"title":["Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations"],"prefix":"10.1145","author":[{"given":"Jimmy","family":"Lin","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueguang","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng-Chieh","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jheng-Hong","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronak","family":"Pradeep","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rodrigo","family":"Nogueira","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"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":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI '16)","author":"Abadi Mart'in","year":"2016","unstructured":"Mart'in Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI '16). 265--283."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR","author":"Yilmaz Zeynep Akkalyoncu","year":"2020","unstructured":"Zeynep Akkalyoncu Yilmaz, Charles L. A. Clarke, and Jimmy Lin. 2020. A Lightweight Environment for Learning Experimental IR Research Practices. In Proceedings of the 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020). 2113--2116."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations","author":"Yilmaz Zeynep Akkalyoncu","year":"2019","unstructured":"Zeynep Akkalyoncu Yilmaz, Shengjin Wang, Wei Yang, Haotian Zhang, and Jimmy Lin. 2019. Applying BERT to Document Retrieval with Birch. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations. Hong Kong, China, 19--24."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2888422.2888439"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2484028.2484132"},{"key":"e_1_3_2_1_6_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268v3","author":"Bajaj Payal","year":"2018","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268v3 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble. arXiv:2010.00200","author":"Bendersky Michael","year":"2020","unstructured":"Michael Bendersky, Honglei Zhuang, Ji Ma, Shuguang Han, Keith Hall, and Ryan McDonald. 2020. RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble. arXiv:2010.00200 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Question Answering, and Abstractive Summarization. arXiv:2006.09595","author":"Esteva Andre","year":"2020","unstructured":"Andre Esteva, Anuprit Kale, Romain Paulus, Kazuma Hashimoto, Wenpeng Yin, Dragomir Radev, and Richard Socher. 2020. CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization. arXiv:2006.09595 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 42nd European Conference on Information Retrieval, Part II (ECIR","author":"Grand Adrien","year":"2020","unstructured":"Adrien Grand, Robert Muir, Jim Ferenczi, and Jimmy Lin. 2020. From Max\u00adScore to Block-Max WAND: The Story of How Lucene Significantly Improved Query Evaluation Performance. In Proceedings of the 42nd European Conference on Information Retrieval, Part II (ECIR 2020). 20--27."},{"key":"e_1_3_2_1_10_1","volume-title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. arXiv:2010.02666","author":"Hofstatter Sebastian","year":"2020","unstructured":"Sebastian Hofstatter, 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_11_1","volume-title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. arXiv:2010.02666","author":"Hofst\u00e4tter Sebastian","year":"2021","unstructured":"Sebastian Hofst\u00e4tter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2021. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. arXiv:2010.02666 (2021)."},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_30"},{"key":"e_1_3_2_1_16_1","volume-title":"2020 a. Pretrained Transformers for Text Ranking: BERT and Beyond. arXiv:2010.06467","author":"Lin Jimmy","year":"2020","unstructured":"Jimmy Lin, Rodrigo Nogueira, and Andrew Yates. 2020 a. Pretrained Transformers for Text Ranking: BERT and Beyond. arXiv:2010.06467 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"2020 b. 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 b. Distilling Dense Representations for Ranking using Tightly-Coupled Teachers. arXiv:2010.11386 (2020)."},{"key":"e_1_3_2_1_18_1","volume-title":"A Replication Study of Dense Passage Retriever. arXiv:2104.05740","author":"Ma Xueguang","year":"2021","unstructured":"Xueguang Ma, Kai Sun, Ronak Pradeep, and Jimmy Lin. 2021. A Replication Study of Dense Passage Retriever. arXiv:2104.05740 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371864"},{"key":"e_1_3_2_1_20_1","volume-title":"Simplified Data Wrangling with textttir_datasets. arXiv:2103.02280","author":"MacAvaney Sean","year":"2021","unstructured":"Sean MacAvaney, Andrew Yates, Sergey Feldman, Doug Downey, Arman Cohan, and Nazli Goharian. 2021. Simplified Data Wrangling with textttir_datasets. arXiv:2103.02280 (2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the SIGIR 2012 Workshop on Open Source Information Retrieval","author":"Macdonald Craig","year":"2012","unstructured":"Craig Macdonald, Richard McCreadie, Rodrygo L.T. Santos, and Iadh Ounis. 2012. From Puppy to Maturity: Experiences in Developing Terrier. In Proceedings of the SIGIR 2012 Workshop on Open Source Information Retrieval. Portland, Oregon."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3409256.3409829"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the Open-Source IR Replicability Challenge (OSIRRC 2019): CEUR Workshop Proceedings Vol-2409","author":"Mallia Antonio","year":"2019","unstructured":"Antonio Mallia, Micha\u0142 Siedlaczek, Joel Mackenzie, and Torsten Suel. 2019. PISA: Performant Indexes and Search for Academia. In Proceedings of the Open-Source IR Replicability Challenge (OSIRRC 2019): CEUR Workshop Proceedings Vol-2409. Paris, France, 50--56."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148246"},{"key":"e_1_3_2_1_26_1","unstructured":"Rodrigo Nogueira and Jimmy Lin. 2019. From doc2query to docTTTTTquery ."},{"key":"e_1_3_2_1_27_1","volume-title":"2019 a. Multi-Stage Document Ranking with BERT. arXiv:1910.14424","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy Lin. 2019 a. Multi-Stage Document Ranking with BERT. arXiv:1910.14424 (2019)."},{"key":"e_1_3_2_1_28_1","volume-title":"2019 b. Document Expansion by Query Prediction. 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:1904.08375 (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems. 8024--8035."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis. 94--103","author":"Pradeep Ronak","year":"2021","unstructured":"Ronak Pradeep, Xueguang Ma, Rodrigo Nogueira, and Jimmy Lin. 2021 a. Scientific Claim Verification with VerT5erini. In Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis. 94--103."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463120"},{"key":"e_1_3_2_1_32_1","volume-title":"2021 c. 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 c. 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_33_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, Vol. 21, 140 (2020), 1--67.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2009934"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_36_1","volume-title":"2020 a. CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search. arXiv:2011.01580","author":"Xiong Chenyan","year":"2020","unstructured":"Chenyan Xiong, Zhenghao Liu, Si Sun, Zhuyun Dai, Kaitao Zhang, Shi Yu, Zhiyuan Liu, Hoifung Poon, Jianfeng Gao, and Paul Bennett. 2020 a. CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search. arXiv:2011.01580 (2020)."},{"key":"e_1_3_2_1_37_1","volume-title":"2020 b. 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 b. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080721"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3239571"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371868"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412780"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the Twenty-Ninth Text REtrieval Conference (TREC","author":"Yu Yongze","year":"2020","unstructured":"Yongze Yu, Jussi Karlgren, Hamed Bonab, Ann Clifton, Md Iftekhar Tanveer, and Rosie Jones. 2020. Spotify at the TREC 2020 Podcasts Track: Segment Retrieval. In Proceedings of the Twenty-Ninth Text REtrieval Conference (TREC 2020)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sdp-1.5"}],"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\/3404835.3463238","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3463238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:44Z","timestamp":1750191464000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3463238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":43,"alternative-id":["10.1145\/3404835.3463238","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3463238","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"}}]}}