{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:29:09Z","timestamp":1774308549577,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"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":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599927","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:13:58Z","timestamp":1691172838000},"page":"4787-4799","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["UnifieR: A Unified Retriever for Large-Scale Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3315-2468","authenticated-orcid":false,"given":"Tao","family":"Shen","sequence":"first","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6477-7933","authenticated-orcid":false,"given":"Xiubo","family":"Geng","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4162-2119","authenticated-orcid":false,"given":"Chongyang","family":"Tao","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1949-5715","authenticated-orcid":false,"given":"Can","family":"Xu","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3740-9515","authenticated-orcid":false,"given":"Guodong","family":"Long","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3850-5429","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-5806","authenticated-orcid":false,"given":"Daxin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Longformer: The Long-Document Transformer. CoRR","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy , Matthew E. Peters , and Arman Cohan . 2020 . Longformer: The Long-Document Transformer. CoRR , Vol. abs\/ 2004 .05150 (2020). [arXiv]2004.05150 https:\/\/arxiv.org\/abs\/2004.05150 Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. Longformer: The Long-Document Transformer. CoRR, Vol. abs\/2004.05150 (2020). [arXiv]2004.05150 https:\/\/arxiv.org\/abs\/2004.05150"},{"key":"e_1_3_2_2_2_1","volume-title":"Semantic Models for the First-stage Retrieval: A Comprehensive Review. CoRR","author":"Cai Yinqiong","year":"2021","unstructured":"Yinqiong Cai , Yixing Fan , Jiafeng Guo , Fei Sun , Ruqing Zhang , and Xueqi Cheng . 2021. Semantic Models for the First-stage Retrieval: A Comprehensive Review. CoRR , Vol. abs\/ 2103 .04831 ( 2021 ). [arXiv]2103.04831 https:\/\/arxiv.org\/abs\/2103.04831 Yinqiong Cai, Yixing Fan, Jiafeng Guo, Fei Sun, Ruqing Zhang, and Xueqi Cheng. 2021. Semantic Models for the First-stage Retrieval: A Comprehensive Review. CoRR, Vol. abs\/2103.04831 (2021). [arXiv]2103.04831 https:\/\/arxiv.org\/abs\/2103.04831"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.338"},{"key":"e_1_3_2_2_5_1","volume-title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? CoRR","author":"Chen Xilun","year":"2021","unstructured":"Xilun Chen , Kushal Lakhotia , Barlas Oguz , Anchit Gupta , Patrick S. H. Lewis , Stan Peshterliev , Yashar Mehdad , Sonal Gupta , and Wen-tau Yih. 2021a. Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? CoRR , Vol. abs\/ 2110 .06918 ( 2021 ). [arXiv]2110.06918 https:\/\/arxiv.org\/abs\/2110.06918 Xilun Chen, Kushal Lakhotia, Barlas Oguz, Anchit Gupta, Patrick S. H. Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta, and Wen-tau Yih. 2021a. Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? CoRR, Vol. abs\/2110.06918 (2021). [arXiv]2110.06918 https:\/\/arxiv.org\/abs\/2110.06918"},{"key":"e_1_3_2_2_6_1","volume-title":"Glass","author":"Chuang Yung-Sung","year":"2022","unstructured":"Yung-Sung Chuang , Rumen Dangovski , Hongyin Luo , Yang Zhang , Shiyu Chang , Marin Soljacic , Shang-Wen Li , Wen-tau Yih, Yoon Kim , and James R . Glass . 2022 . DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings. CoRR , Vol. abs\/ 2204 .10298 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.10298 [arXiv]2204.10298 10.48550\/arXiv.2204.10298 Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo, Yang Zhang, Shiyu Chang, Marin Soljacic, Shang-Wen Li, Wen-tau Yih, Yoon Kim, and James R. Glass. 2022. DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings. CoRR, Vol. abs\/2204.10298 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.10298 [arXiv]2204.10298"},{"key":"e_1_3_2_2_7_1","volume-title":"Overview of the TREC 2019 deep learning track. CoRR","volume":"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. CoRR , Vol. abs\/ 2003 .07820 ( 2020 ). [arXiv]2003.07820 https:\/\/arxiv.org\/abs\/2003.07820 Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, and Ellen M. Voorhees. 2020. Overview of the TREC 2019 deep learning track. CoRR, Vol. abs\/2003.07820 (2020). [arXiv]2003.07820 https:\/\/arxiv.org\/abs\/2003.07820"},{"key":"e_1_3_2_2_8_1","volume-title":"abs\/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 . Co RR , Vol . abs\/1910.10687 ( 2019 ). [arXiv]1910.10687 http:\/\/arxiv.org\/abs\/1910.10687 Zhuyun Dai and Jamie Callan. 2019. Context-Aware Sentence\/Passage Term Importance Estimation For First Stage Retrieval. CoRR, Vol. abs\/1910.10687 (2019). [arXiv]1910.10687 http:\/\/arxiv.org\/abs\/1910.10687"},{"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, NAACL-HLT 2019","volume":"1","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, NAACL-HLT 2019 , Minneapolis, MN, USA , June 2-7, 2019, Volume 1 (Long and Short Papers), Jill Burstein, Christy Doran, and Thamar Solorio (Eds.). Association for Computational Linguistics, 4171--4186. https:\/\/doi.org\/10.18653\/v1\/n19--1423 10.18653\/v1 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, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), Jill Burstein, Christy Doran, and Thamar Solorio (Eds.). Association for Computational Linguistics, 4171--4186. https:\/\/doi.org\/10.18653\/v1\/n19--1423"},{"key":"e_1_3_2_2_10_1","volume-title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. CoRR","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal , Carlos Lassance , Benjamin Piwowarski , and St\u00e9 phane Clinchant . 2021a. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. CoRR , Vol. abs\/ 2109 .10086 ( 2021 ). [arXiv]2109.10086 https:\/\/arxiv.org\/abs\/2109.10086 Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and St\u00e9 phane Clinchant. 2021a. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. CoRR, Vol. abs\/2109.10086 (2021). [arXiv]2109.10086 https:\/\/arxiv.org\/abs\/2109.10086"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531857"},{"key":"e_1_3_2_2_12_1","volume-title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal , Benjamin Piwowarski , and St\u00e9phane Clinchant . 2021 b. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , Virtual Event, Canada , July 11-15, 2021, Fernando Diaz, Chirag Shah, Torsten Suel, Pablo Castells, Rosie Jones, and Tetsuya Sakai (Eds.). ACM, 2288--2292. https:\/\/doi.org\/10.1145\/3404835.3463098 10.1145\/3404835.3463098 Thibault Formal, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021b. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, Fernando Diaz, Chirag Shah, Torsten Suel, Pablo Castells, Rosie Jones, and Tetsuya Sakai (Eds.). ACM, 2288--2292. https:\/\/doi.org\/10.1145\/3404835.3463098"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"e_1_3_2_2_14_1","volume-title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval. CoRR","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao and Jamie Callan . 2021b. Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval. CoRR , Vol. abs\/ 2108 .05540 ( 2021 ). [arXiv]2108.05540 https:\/\/arxiv.org\/abs\/2108.05540 Luyu Gao and Jamie Callan. 2021b. Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval. CoRR, Vol. abs\/2108.05540 (2021). [arXiv]2108.05540 https:\/\/arxiv.org\/abs\/2108.05540"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.241"},{"key":"e_1_3_2_2_16_1","volume-title":"ECIR 2021, Virtual Event, March 28 - April 1, 2021, Proceedings, Part I (Lecture Notes in Computer Science","volume":"160","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao , Zhuyun Dai , Tongfei Chen , Zhen Fan , Benjamin Van Durme , and Jamie Callan . 2021 b. Complement Lexical Retrieval Model with Semantic Residual Embeddings. In Advances in Information Retrieval - 43rd European Conference on IR Research , ECIR 2021, Virtual Event, March 28 - April 1, 2021, Proceedings, Part I (Lecture Notes in Computer Science , Vol. 12656), Djoerd Hiemstra, Marie-Francine Moens, Josiane Mothe, Raffaele Perego, Martin Potthast, and Fabrizio Sebastiani (Eds.). Springer, 146-- 160 . https:\/\/doi.org\/10.1007\/978-3-030-72113-8_10 10.1007\/978-3-030-72113-8_10 Luyu Gao, Zhuyun Dai, Tongfei Chen, Zhen Fan, Benjamin Van Durme, and Jamie Callan. 2021b. Complement Lexical Retrieval Model with Semantic Residual Embeddings. In Advances in Information Retrieval - 43rd European Conference on IR Research, ECIR 2021, Virtual Event, March 28 - April 1, 2021, Proceedings, Part I (Lecture Notes in Computer Science, Vol. 12656), Djoerd Hiemstra, Marie-Francine Moens, Josiane Mothe, Raffaele Perego, Martin Potthast, and Fabrizio Sebastiani (Eds.). Springer, 146--160. https:\/\/doi.org\/10.1007\/978-3-030-72113-8_10"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_2_2_18_1","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018","author":"Han Bo","year":"2018","unstructured":"Bo Han , Quanming Yao , Xingrui Yu , Gang Niu , Miao Xu , Weihua Hu , Ivor W. Tsang , and Masashi Sugiyama . 2018 . Co-teaching: Robust training of deep neural networks with extremely noisy labels . In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018 , NeurIPS 2018, December 3-8, 2018, Montr\u00e9al, Canada, Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicol\u00f2 Cesa-Bianchi, and Roman Garnett (Eds.). 8536--8546. https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/a19744e268754fb0148b017647355b7b-Abstract.html Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor W. Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr\u00e9al, Canada, Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicol\u00f2 Cesa-Bianchi, and Roman Garnett (Eds.). 8536--8546. https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/a19744e268754fb0148b017647355b7b-Abstract.html"},{"key":"e_1_3_2_2_19_1","volume-title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. CoRR","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. CoRR , Vol. abs\/ 2010 .02666 ( 2020 ). [arXiv]2010.02666 https:\/\/arxiv.org\/abs\/2010.02666 Sebastian Hofst\u00e4tter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. CoRR, Vol. abs\/2010.02666 (2020). [arXiv]2010.02666 https:\/\/arxiv.org\/abs\/2010.02666"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_2_21_1","volume-title":"Towards Unsupervised Dense Information Retrieval with Contrastive Learning. CoRR","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard , Mathilde Caron , Lucas Hosseini , Sebastian Riedel , Piotr Bojanowski , Armand Joulin , and Edouard Grave . 2021. Towards Unsupervised Dense Information Retrieval with Contrastive Learning. CoRR , Vol. abs\/ 2112 .09118 ( 2021 ). [arXiv]2112.09118 https:\/\/arxiv.org\/abs\/2112.09118 Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Towards Unsupervised Dense Information Retrieval with Contrastive Learning. CoRR, Vol. abs\/2112.09118 (2021). [arXiv]2112.09118 https:\/\/arxiv.org\/abs\/2112.09118"},{"key":"e_1_3_2_2_22_1","volume-title":"Instance-aware Prompt Learning for Language Understanding and Generation. CoRR","author":"Jin Feihu","year":"2022","unstructured":"Feihu Jin , Jinliang Lu , Jiajun Zhang , and Chengqing Zong . 2022. Instance-aware Prompt Learning for Language Understanding and Generation. CoRR , Vol. abs\/ 2201 .07126 ( 2022 ). [arXiv]2201.07126 https:\/\/arxiv.org\/abs\/2201.07126 Feihu Jin, Jinliang Lu, Jiajun Zhang, and Chengqing Zong. 2022. Instance-aware Prompt Learning for Language Understanding and Generation. CoRR, Vol. abs\/2201.07126 (2022). [arXiv]2201.07126 https:\/\/arxiv.org\/abs\/2201.07126"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_2_25_1","volume-title":"Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach. CoRR","author":"Kuzi Saar","year":"2020","unstructured":"Saar Kuzi , Mingyang Zhang , Cheng Li , Michael Bendersky , and Marc Najork . 2020. Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach. CoRR , Vol. abs\/ 2010 .01195 ( 2020 ). [arXiv]2010.01195 https:\/\/arxiv.org\/abs\/2010.01195 Saar Kuzi, Mingyang Zhang, Cheng Li, Michael Bendersky, and Marc Najork. 2020. Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach. CoRR, Vol. abs\/2010.01195 (2020). [arXiv]2010.01195 https:\/\/arxiv.org\/abs\/2010.01195"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.85"},{"key":"e_1_3_2_2_27_1","volume-title":"R-Drop: Regularized Dropout for Neural Networks. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Liang Xiaobo","year":"2021","unstructured":"Xiaobo Liang , Lijun Wu , Juntao Li , Yue Wang , Qi Meng , Tao Qin , Wei Chen , Min Zhang , and Tie-Yan Liu . 2021 . R-Drop: Regularized Dropout for Neural Networks. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021 , NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 10890--10905. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/5a66b9200f29ac3fa0ae244cc2a51b39-Abstract.html Xiaobo Liang, Lijun Wu, Juntao Li, Yue Wang, Qi Meng, Tao Qin, Wei Chen, Min Zhang, and Tie-Yan Liu. 2021. R-Drop: Regularized Dropout for Neural Networks. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 10890--10905. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/5a66b9200f29ac3fa0ae244cc2a51b39-Abstract.html"},{"key":"e_1_3_2_2_28_1","volume-title":"COIL, and a Conceptual Framework for Information Retrieval Techniques. CoRR","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. CoRR , Vol. abs\/ 2106 .14807 ( 2021 ). [arXiv]2106.14807 https:\/\/arxiv.org\/abs\/2106.14807 Jimmy Lin and Xueguang Ma. 2021. A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques. CoRR, Vol. abs\/2106.14807 (2021). [arXiv]2106.14807 https:\/\/arxiv.org\/abs\/2106.14807"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.17"},{"key":"e_1_3_2_2_30_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR","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. CoRR , Vol. abs\/ 1907 .11692 ( 2019 ). [arXiv]1907.11692 http:\/\/arxiv.org\/abs\/1907.11692 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. CoRR, Vol. abs\/1907.11692 (2019). [arXiv]1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_2_31_1","volume-title":"Less is More: Pre-training a Strong Siamese Encoder Using a Weak Decoder. CoRR","author":"Lu Shuqi","year":"2021","unstructured":"Shuqi Lu , Chenyan Xiong , Di He , Guolin Ke , Waleed Malik , Zhicheng Dou , Paul Bennett , Tie-Yan Liu , and Arnold Overwijk . 2021. Less is More: Pre-training a Strong Siamese Encoder Using a Weak Decoder. CoRR , Vol. abs\/ 2102 .09206 ( 2021 ). [arXiv]2102.09206 https:\/\/arxiv.org\/abs\/2102.09206 Shuqi Lu, Chenyan Xiong, Di He, Guolin Ke, Waleed Malik, Zhicheng Dou, Paul Bennett, Tie-Yan Liu, and Arnold Overwijk. 2021. Less is More: Pre-training a Strong Siamese Encoder Using a Weak Decoder. CoRR, Vol. abs\/2102.09206 (2021). [arXiv]2102.09206 https:\/\/arxiv.org\/abs\/2102.09206"},{"key":"e_1_3_2_2_32_1","volume-title":"Sashank J Reddi, and Sanjiv Kumar.","author":"Menon Aditya Krishna","year":"2021","unstructured":"Aditya Krishna Menon , Sadeep Jayasumana , Seungyeon Kim , Ankit Singh Rawat , Sashank J Reddi, and Sanjiv Kumar. 2021 . In de fense of dual-encoders for neural ranking. (2021). Aditya Krishna Menon, Sadeep Jayasumana, Seungyeon Kim, Ankit Singh Rawat, Sashank J Reddi, and Sanjiv Kumar. 2021. In defense of dual-encoders for neural ranking. (2021)."},{"key":"e_1_3_2_2_33_1","volume-title":"SGPT: GPT Sentence Embeddings for Semantic Search. CoRR","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff . 2022 . SGPT: GPT Sentence Embeddings for Semantic Search. CoRR , Vol. abs\/ 2202 .08904 (2022). [arXiv]2202.08904 https:\/\/arxiv.org\/abs\/2202.08904 Niklas Muennighoff. 2022. SGPT: GPT Sentence Embeddings for Semantic Search. CoRR, Vol. abs\/2202.08904 (2022). [arXiv]2202.08904 https:\/\/arxiv.org\/abs\/2202.08904"},{"key":"e_1_3_2_2_34_1","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. In Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016) Barcelona Spain December 9 2016 (CEUR Workshop Proceedings Vol. 1773) Tarek Richard Besold Antoine Bordes Artur S. d'Avila Garcez and Greg Wayne (Eds.). CEUR-WS.org. http:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf  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. In Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016) Barcelona Spain December 9 2016 (CEUR Workshop Proceedings Vol. 1773) Tarek Richard Besold Antoine Bordes Artur S. d'Avila Garcez and Greg Wayne (Eds.). CEUR-WS.org. http:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"key":"e_1_3_2_2_35_1","volume-title":"Large Dual Encoders Are Generalizable Retrievers. CoRR","author":"Ni Jianmo","year":"2021","unstructured":"Jianmo Ni , Chen Qu , Jing Lu , Zhuyun Dai , Gustavo Hern\u00e1ndez \u00c1brego , Ji Ma , Vincent Y. Zhao , Yi Luan , Keith B. Hall , Ming-Wei Chang , and Yinfei Yang . 2021. Large Dual Encoders Are Generalizable Retrievers. CoRR , Vol. abs\/ 2112 .07899 ( 2021 ). [arXiv]2112.07899 https:\/\/arxiv.org\/abs\/2112.07899 Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hern\u00e1ndez \u00c1brego, Ji Ma, Vincent Y. Zhao, Yi Luan, Keith B. Hall, Ming-Wei Chang, and Yinfei Yang. 2021. Large Dual Encoders Are Generalizable Retrievers. CoRR, Vol. abs\/2112.07899 (2021). [arXiv]2112.07899 https:\/\/arxiv.org\/abs\/2112.07899"},{"key":"e_1_3_2_2_36_1","volume-title":"From doc2query to docTTTTTquery. Online preprint","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira , Jimmy Lin , and AI Epistemic . 2019. From doc2query to docTTTTTquery. Online preprint , Vol. 6 ( 2019 ). Rodrigo Nogueira, Jimmy Lin, and AI Epistemic. 2019. From doc2query to docTTTTTquery. Online preprint, Vol. 6 (2019)."},{"key":"e_1_3_2_2_37_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Paria Biswajit","year":"2020","unstructured":"Biswajit Paria , Chih-Kuan Yeh , Ian En-Hsu Yen , Ning Xu , Pradeep Ravikumar , and Barnab\u00e1s P\u00f3czos . 2020 . Minimizing FLOPs to Learn Efficient Sparse Representations . In 8th International Conference on Learning Representations, ICLR 2020 , Addis Ababa, Ethiopia , April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=SygpC6Ntvr Biswajit Paria, Chih-Kuan Yeh, Ian En-Hsu Yen, Ning Xu, Pradeep Ravikumar, and Barnab\u00e1s P\u00f3czos. 2020. Minimizing FLOPs to Learn Efficient Sparse Representations. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=SygpC6Ntvr"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.191"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_2_43_1","volume-title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. CoRR","author":"Santhanam Keshav","year":"2021","unstructured":"Keshav Santhanam , Omar Khattab , Jon Saad-Falcon , Christopher Potts , and Matei Zaharia . 2021. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. CoRR , Vol. abs\/ 2112 .01488 ( 2021 ). [arXiv]2112.01488 https:\/\/arxiv.org\/abs\/2112.01488 Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, and Matei Zaharia. 2021. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. CoRR, Vol. abs\/2112.01488 (2021). [arXiv]2112.01488 https:\/\/arxiv.org\/abs\/2112.01488"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1127"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.160"},{"key":"e_1_3_2_2_46_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Sun Zhiqing","year":"2019","unstructured":"Zhiqing Sun , Zhi-Hong Deng , Jian-Yun Nie , and Jian Tang . 2019 . RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space . In 7th International Conference on Learning Representations, ICLR 2019 , New Orleans, LA, USA , May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=HkgEQnRqYQ Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. 2019. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=HkgEQnRqYQ"},{"key":"e_1_3_2_2_47_1","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever , Oriol Vinyals , and Quoc V. Le . 2014. Sequence to Sequence Learning with Neural Networks . In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014 , December 8-13 2014 , Montreal, Quebec, Canada, Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D. Lawrence, and Kilian Q. Weinberger (Eds.). 3104--3112. https:\/\/proceedings.neurips.cc\/paper\/ 2014\/hash\/a14ac55a4f27472c5d894ec1c3c743d2-Abstract.html Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada, Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D. Lawrence, and Kilian Q. Weinberger (Eds.). 3104--3112. https:\/\/proceedings.neurips.cc\/paper\/2014\/hash\/a14ac55a4f27472c5d894ec1c3c743d2-Abstract.html"},{"key":"e_1_3_2_2_48_1","volume-title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. CoRR","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur , Nils Reimers , Andreas R\u00fcckl\u00e9 , Abhishek Srivastava , and Iryna Gurevych . 2021 . BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. CoRR , Vol. abs\/ 2104 .08663 (2021). [arXiv]2104.08663 https:\/\/arxiv.org\/abs\/2104.08663 Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. CoRR, Vol. abs\/2104.08663 (2021). [arXiv]2104.08663 https:\/\/arxiv.org\/abs\/2104.08663"},{"key":"e_1_3_2_2_49_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","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 Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017 , December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998--6008. https:\/\/proceedings.neurips.cc\/paper\/ 2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html 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 Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998--6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_2_50_1","volume-title":"IDPG: An Instance-Dependent Prompt Generation Method. CoRR","author":"Wu Zhuofeng","year":"2022","unstructured":"Zhuofeng Wu , Sinong Wang , Jiatao Gu , Rui Hou , Yuxiao Dong , V. G. Vinod Vydiswaran , and Hao Ma . 2022 . IDPG: An Instance-Dependent Prompt Generation Method. CoRR , Vol. abs\/ 2204 .04497 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.04497 [arXiv]2204.04497 10.48550\/arXiv.2204.04497 Zhuofeng Wu, Sinong Wang, Jiatao Gu, Rui Hou, Yuxiao Dong, V. G. Vinod Vydiswaran, and Hao Ma. 2022. IDPG: An Instance-Dependent Prompt Generation Method. CoRR, Vol. abs\/2204.04497 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.04497 [arXiv]2204.04497"},{"key":"e_1_3_2_2_51_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In 9th International Conference on Learning Representations, ICLR 2021","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 9th International Conference on Learning Representations, ICLR 2021 , Virtual Event, Austria , May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=zeFrfgyZln 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 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_2_52_1","volume-title":"Sparsifying Sparse Representations for Passage Retrieval by Top-k Masking. CoRR","author":"Yang Jheng-Hong","year":"2021","unstructured":"Jheng-Hong Yang , Xueguang Ma , and Jimmy Lin . 2021. Sparsifying Sparse Representations for Passage Retrieval by Top-k Masking. CoRR , Vol. abs\/ 2112 .09628 ( 2021 ). [arXiv]2112.09628 https:\/\/arxiv.org\/abs\/2112.09628 Jheng-Hong Yang, Xueguang Ma, and Jimmy Lin. 2021. Sparsifying Sparse Representations for Passage Retrieval by Top-k Masking. CoRR, Vol. abs\/2112.09628 (2021). [arXiv]2112.09628 https:\/\/arxiv.org\/abs\/2112.09628"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080721"},{"key":"e_1_3_2_2_54_1","volume-title":"Optimizing Dense Retrieval Model Training with Hard Negatives. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Zhan Jingtao","year":"2021","unstructured":"Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Jiafeng Guo , Min Zhang , and Shaoping Ma . 2021 . Optimizing Dense Retrieval Model Training with Hard Negatives. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , Virtual Event, Canada , July 11-15, 2021, Fernando Diaz, Chirag Shah, Torsten Suel, Pablo Castells, Rosie Jones, and Tetsuya Sakai (Eds.). ACM, 1503--1512. https:\/\/doi.org\/10.1145\/3404835.3462880 10.1145\/3404835.3462880 Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021. Optimizing Dense Retrieval Model Training with Hard Negatives. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, Fernando Diaz, Chirag Shah, Torsten Suel, Pablo Castells, Rosie Jones, and Tetsuya Sakai (Eds.). ACM, 1503--1512. https:\/\/doi.org\/10.1145\/3404835.3462880"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498443"},{"key":"e_1_3_2_2_56_1","volume-title":"Adversarial Retriever-Ranker for Dense Text Retrieval. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=MR7XubKUFB","author":"Zhang Hang","year":"2022","unstructured":"Hang Zhang , Yeyun Gong , Yelong Shen , Jiancheng Lv , Nan Duan , and Weizhu Chen . 2022 . Adversarial Retriever-Ranker for Dense Text Retrieval. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=MR7XubKUFB Hang Zhang, Yeyun Gong, Yelong Shen, Jiancheng Lv, Nan Duan, and Weizhu Chen. 2022. Adversarial Retriever-Ranker for Dense Text Retrieval. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=MR7XubKUFB"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.493"}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599927","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:42Z","timestamp":1750178262000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599927"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":57,"alternative-id":["10.1145\/3580305.3599927","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599927","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}