{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:57:18Z","timestamp":1772913438067,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":41,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236004"],"award-info":[{"award-number":["62236004"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0106500"],"award-info":[{"award-number":["2020AAA0106500"]}],"id":[{"id":"10.13039\/501100012166","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\/3539618.3591813","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"3160-3164","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["OpenMatch-v2: An All-in-one Multi-Modality PLM-based Information Retrieval Toolkit"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6335-1076","authenticated-orcid":false,"given":"Shi","family":"Yu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0083-3224","authenticated-orcid":false,"given":"Zhenghao","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0392-4183","authenticated-orcid":false,"given":"Chenyan","family":"Xiong","sequence":"additional","affiliation":[{"name":"Microsoft Research, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7709-2543","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"MS MARCO: A human generated MAchine Reading COmprehension dataset. arXiv preprint arXiv:1611.09268","author":"Bajaj Payal","year":"2016","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, et al. 2016. MS MARCO: A human generated MAchine Reading COmprehension dataset. arXiv preprint arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_1_2_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of NAACL. 4171--4186","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 NAACL. 4171--4186."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Zhangyin Feng Daya Guo Duyu Tang Nan Duan Xiaocheng Feng Ming Gong Linjun Shou Bing Qin Ting Liu Daxin Jiang et al. 2020. CodeBERT: A Pre-Trained Model for Programming and Natural Languages. In Findings of EMNLP. 1536--1547.","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"e_1_3_2_1_7_1","volume-title":"Tevatron: An efficient and flexible toolkit for dense retrieval. arXiv preprint arXiv:2203.05765","author":"Gao Luyu","year":"2022","unstructured":"Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2022. Tevatron: An efficient and flexible toolkit for dense retrieval. arXiv preprint arXiv:2203.05765 (2022)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331403"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_10_1","volume-title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search. CoRR","author":"Husain Hamel","year":"2019","unstructured":"Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, and Marc Brockschmidt. 2019. CodeSearchNet Challenge: Evaluating the State of Semantic Code Search. CoRR (2019)."},{"key":"e_1_3_2_1_11_1","unstructured":"Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. 2021. Unsupervised Dense Information Retrieval with Contrastive Learning."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"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","first-page":"452","article-title":"Natural Questions: a Benchmark for Question Answering Research","volume":"7","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur P. Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural Questions: a Benchmark for Question Answering Research. Transactions of the ACL, Vol. 7 (2019), 452--466.","journal-title":"Transactions of the ACL"},{"key":"e_1_3_2_1_15_1","volume-title":"Yacine Jernite, Abhishek Thakur, Patrick von Platen, Suraj Patil, Julien Chaumond, Mariama Drame, Julien Plu, Lewis Tunstall, et al.","author":"Lhoest Quentin","year":"2021","unstructured":"Quentin Lhoest, Albert Villanova del Moral, Yacine Jernite, Abhishek Thakur, Patrick von Platen, Suraj Patil, Julien Chaumond, Mariama Drame, Julien Plu, Lewis Tunstall, et al. 2021. Datasets: A Community Library for Natural Language Processing. In Proceedings of EMNLP: System Demonstrations. 175--184."},{"key":"e_1_3_2_1_16_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","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_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462789"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.220"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.92"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.669"},{"key":"e_1_3_2_1_21_1","volume-title":"Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Rodrigo Nogueira Zhiying Jiang Ronak Pradeep and Jimmy Lin. 2020. Document Ranking with a Pretrained Sequence-to-Sequence Model. In Findings of the EMNLP. 708--718.","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.200"},{"key":"e_1_3_2_1_24_1","volume-title":"Understanding the Behaviors of BERT in Ranking. arXiv preprint arXiv:1904.07531","author":"Qiao Yifan","year":"2019","unstructured":"Yifan Qiao, Chenyan Xiong, Zhenghao Liu, and Zhiyuan Liu. 2019. Understanding the Behaviors of BERT in Ranking. arXiv preprint arXiv:1904.07531 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_26_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. J. Mach. Learn. Res., Vol. 21 (2020), 140:1--140:67.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_27_1","volume-title":"Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search. CoRR","author":"Reddy Chandan K.","year":"2022","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. CoRR (2022)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa091"},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"Proceedings of EMNLP","author":"Si Sun","year":"2022","unstructured":"Sun Si, Xiong Chenyan, Yu Yue, Overwijk Arnold, Liu Zhiyuan, and Bao Jie. 2022. Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives. In Proceedings of EMNLP 2022."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.390"},{"key":"e_1_3_2_1_34_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In NeurIPS.","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In NeurIPS."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.168"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080809"},{"key":"e_1_3_2_1_39_1","unstructured":"Lee Xiong Chenyan Xiong Ye Li Kwok-Fung Tang Jialin Liu Paul N. Bennett Junaid Ahmed and Arnold Overwikj. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In ICLR."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462856"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380131"}],"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\/3539618.3591813","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:58Z","timestamp":1750178278000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591813"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":41,"alternative-id":["10.1145\/3539618.3591813","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591813","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"}}]}}