{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T10:03:26Z","timestamp":1763114606278,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"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":[[2023,11,26]]},"DOI":"10.1145\/3624918.3625334","type":"proceedings-article","created":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T08:49:17Z","timestamp":1700729357000},"page":"150-157","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Sparse Retrieval via Unsupervised Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3430-4910","authenticated-orcid":false,"given":"Xueguang","family":"Ma","sequence":"first","affiliation":[{"name":"University of Waterloo, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0157-0017","authenticated-orcid":false,"given":"Hengxin","family":"Fun","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8170-6934","authenticated-orcid":false,"given":"Xusen","family":"Yin","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7817-6140","authenticated-orcid":false,"given":"Antonio","family":"Mallia","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7189","authenticated-orcid":false,"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"key":"e_1_3_2_1_1_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_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401204"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","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, Volume 1 (Long and Short Papers). Minneapolis, Minnesota, 4171\u20134186."},{"key":"e_1_3_2_1_6_1","volume-title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. arXiv:2109.10086","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, C. Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. arXiv:2109.10086 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval. arXiv:2108.05540","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao and Jamie Callan. 2021. Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval. arXiv:2108.05540 (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591805"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.31"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_11_1","volume-title":"Unsupervised Dense Information Retrieval with Contrastive Learning. arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised Dense Information Retrieval with Contrastive Learning. arXiv:2112.09118 (2021)."},{"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\/P17-1147"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1612"},{"key":"e_1_3_2_1_17_1","volume-title":"A Proposed Conceptual Framework for a Representational Approach to Information Retrieval. arXiv:2110.01529","author":"Lin Jimmy","year":"2021","unstructured":"Jimmy Lin. 2021. A Proposed Conceptual Framework for a Representational Approach to Information Retrieval. arXiv:2110.01529 (2021)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"volume-title":"Pretrained Transformers for Text Ranking: BERT and Beyond","author":"Lin Jimmy","key":"e_1_3_2_1_19_1","unstructured":"Jimmy Lin, Rodrigo Nogueira, and Andrew Yates. 2021. Pretrained Transformers for Text Ranking: BERT and Beyond. Morgan & Claypool Publishers."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.17"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531749"},{"key":"e_1_3_2_1_22_1","volume-title":"Wacky Weights in Learned Sparse Representations and the Revenge of Score-at-a-Time Query Evaluation. arXiv:2110.11540","author":"Mackenzie Joel","year":"2021","unstructured":"Joel Mackenzie, Andrew Trotman, and Jimmy Lin. 2021. Wacky Weights in Learned Sparse Representations and the Revenge of Score-at-a-Time Query Evaluation. arXiv:2110.11540 (2021)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463030"},{"key":"e_1_3_2_1_24_1","volume-title":"Tyna\u00a0Eloundou Nekoul, Girish Sastry, Gretchen Krueger, David Schnurr, Felipe\u00a0Petroski Such, Kenny Hsu, Madeleine Thompson, Tabarak Khan, Toki Sherbakov, Joanne Jang, Peter Welinder, and Lilian Weng.","author":"Neelakantan Arvind","year":"2022","unstructured":"Arvind Neelakantan, Tao Xu, Raul Puri, Alec Radford, Jesse\u00a0Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong\u00a0Wook Kim, Chris Hallacy, Johannes Heidecke, Pranav Shyam, Boris Power, Tyna\u00a0Eloundou Nekoul, Girish Sastry, Gretchen Krueger, David Schnurr, Felipe\u00a0Petroski Such, Kenny Hsu, Madeleine Thompson, Tabarak Khan, Toki Sherbakov, Joanne Jang, Peter Welinder, and Lilian Weng. 2022. Text and Code Embeddings by Contrastive Pre-Training. arXiv:2201.10005 (2022)."},{"key":"e_1_3_2_1_25_1","volume-title":"Minimizing FLOPs to Learn Efficient Sparse Representations. arXiv:2004.05665","author":"Paria Biswajit","year":"2020","unstructured":"Biswajit Paria, Chih-Kuan Yeh, Ning Xu, Barnab\u00e1s P\u00f3czos, Pradeep Ravikumar, and Ian En-Hsu Yen. 2020. Minimizing FLOPs to Learn Efficient Sparse Representations. arXiv:2004.05665 (2020)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_28_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","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 Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul\u00a0N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In Proceedings of the 9th International Conference on Learning Representations (ICLR 2021)."},{"key":"e_1_3_2_1_30_1","volume-title":"Sparsifying Sparse Representations for Passage Retrieval by Top-k Masking. arXiv:2112.09628","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. arXiv:2112.09628 (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080721"},{"key":"e_1_3_2_1_32_1","volume-title":"Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion. arXiv:2108.08513","author":"Zhuang Shengyao","year":"2021","unstructured":"Shengyao Zhuang and Guido Zuccon. 2021. Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion. arXiv:2108.08513 (2021)."}],"event":{"name":"SIGIR-AP '23: Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Beijing China","acronym":"SIGIR-AP '23"},"container-title":["Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624918.3625334","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624918.3625334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T21:33:17Z","timestamp":1755898397000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624918.3625334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"references-count":32,"alternative-id":["10.1145\/3624918.3625334","10.1145\/3624918"],"URL":"https:\/\/doi.org\/10.1145\/3624918.3625334","relation":{},"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"2023-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}