{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:14:50Z","timestamp":1783696490913,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809724","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"403-414","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8100-2079","authenticated-orcid":false,"given":"Zhichao","family":"Geng","sequence":"first","affiliation":[{"name":"Amazon Web Service, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2480-3339","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Amazon Web Service, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.421"},{"key":"e_1_3_2_1_2_1","volume-title":"SparTerm: Learning term-based sparse representation for fast text retrieval. arXiv preprint arXiv:2010.00768","author":"Bai Yang","year":"2020","unstructured":"Yang Bai, Xiaoguang Li, Gang Wang, Chaoliang Zhang, Lifeng Shang, Jun Xu, Zhaowei Wang, Fangshan Wang, and Qun Liu. 2020. SparTerm: Learning term-based sparse representation for fast text retrieval. arXiv preprint arXiv:2010.00768 (2020)."},{"key":"e_1_3_2_1_3_1","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett Peter L.","year":"2002","unstructured":"Peter L. Bartlett and Shahar Mendelson. 2002. Rademacher and Gaussian complexities: Risk bounds and structural results. Journal of Machine Learning Research, Vol. 3 (2002), 463-482.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_4_1","volume-title":"dolma-chem-only-query-generated. Hugging Face Datasets. https:\/\/huggingface.co\/datasets\/BASF-AI\/dolma-chem-only-query-generated Chemistry-focused query-generated subset","author":"BASF-AI.","year":"2025","unstructured":"BASF-AI. 2025. dolma-chem-only-query-generated. Hugging Face Datasets. https:\/\/huggingface.co\/datasets\/BASF-AI\/dolma-chem-only-query-generated Chemistry-focused query-generated subset; accessed 2025-12-26."},{"key":"e_1_3_2_1_5_1","volume-title":"Deeperimpact: Optimizing sparse learned index structures. arXiv preprint arXiv:2405.17093","author":"Basnet Soyuj","year":"2024","unstructured":"Soyuj Basnet, Jerry Gou, Antonio Mallia, and Torsten Suel. 2024. Deeperimpact: Optimizing sparse learned index structures. arXiv preprint arXiv:2405.17093 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_1_7_1","volume-title":"Overview of the TREC 2022 deep learning track. arXiv preprint arXiv:2507","author":"Craswell Nick","year":"2025","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, Jimmy Lin, Ellen M Voorhees, and Ian Soboroff. 2025. Overview of the TREC 2022 deep learning track. arXiv preprint arXiv:2507.10865 (2025)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401204"},{"key":"e_1_3_2_1_9_1","first-page":"4171","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). 4171-4186."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.829"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615207"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.609"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Thibault Formal Carlos Lassance Benjamin Piwowarski and St\u00e9phane Clinchant. 2021a. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. doi:10.48550\/ARXIV.2109.10086","DOI":"10.48550\/ARXIV.2109.10086"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531857"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"e_1_3_2_1_17_1","volume-title":"COIL: Revisit exact lexical match in information retrieval with contextualized inverted list. arXiv preprint arXiv:2104.07186","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao, Zhuyun Dai, and Jamie Callan. 2021. COIL: Revisit exact lexical match in information retrieval with contextualized inverted list. arXiv preprint arXiv:2104.07186 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"Towards competitive search relevance for inference-free learned sparse retrievers. arXiv preprint arXiv:2411.04403","author":"Geng Zhichao","year":"2024","unstructured":"Zhichao Geng, Yiwen Wang, Dongyu Ru, and Yang Yang. 2024. Towards competitive search relevance for inference-free learned sparse retrievers. arXiv preprint arXiv:2411.04403 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Johnson","author":"Horn Roger A.","year":"2013","unstructured":"Roger A. Horn and Charles R. Johnson. 2013. Matrix Analysis (2 ed.). Cambridge University Press."},{"key":"e_1_3_2_1_20_1","volume-title":"Margin Bounds, and Regularization. In Advances in Neural Information Processing Systems 21, Daphne Koller, Dale Schuurmans, Yoshua Bengio, and L\u00e9on Bottou (Eds.). Curran Associates","author":"Kakade Sham M.","year":"2008","unstructured":"Sham M. Kakade, Karthik Sridharan, and Ambuj Tewari. 2008. On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization. In Advances in Neural Information Processing Systems 21, Daphne Koller, Dale Schuurmans, Yoshua Bengio, and L\u00e9on Bottou (Eds.). Curran Associates, Inc., Vancouver, Canada, 793-800. https:\/\/proceedings.neurips.cc\/paper\/2008\/hash\/5b69b9cb83065d403869739ae7f0995e-Abstract.html"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_23_1","volume-title":"Nick Sherck, Stephen Dokas, Hamidreza Mahyar, and Soheila Samiee.","author":"Kasmaee Ali Shiraee","year":"2024","unstructured":"Ali Shiraee Kasmaee, Mohammad Khodadad, Mohammad Arshi Saloot, Nick Sherck, Stephen Dokas, Hamidreza Mahyar, and Soheila Samiee. 2024. ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain. arXiv preprint arXiv:2412.00532 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Tae Kwan Lee, and Taeryun Won","author":"Kim Hiun","year":"2025","unstructured":"Hiun Kim, Tae Kwan Lee, and Taeryun Won. 2025. The Role of Vocabularies in Learning Sparse Representations for Ranking. arXiv preprint arXiv:2509.16621 (2025)."},{"key":"e_1_3_2_1_25_1","volume-title":"Subword regularization: Improving neural network translation models with multiple subword candidates. arXiv preprint arXiv:1804.10959","author":"Kudo Taku","year":"2018","unstructured":"Taku Kudo. 2018. Subword regularization: Improving neural network translation models with multiple subword candidates. arXiv preprint arXiv:1804.10959 (2018)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531833"},{"key":"e_1_3_2_1_27_1","volume-title":"SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789","author":"Lassance Carlos","year":"2024","unstructured":"Carlos Lassance, Herv\u00e9 D\u00e9jean, Thibault Formal, and St\u00e9phane Clinchant. 2024. SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20212-4"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.930"},{"key":"e_1_3_2_1_30_1","volume-title":"A few brief notes on deepimpact, coil, and a conceptual framework for information retrieval techniques. arXiv preprint arXiv:2106.14807","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. arXiv preprint arXiv:2106.14807 (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-21289-4_33"},{"key":"e_1_3_2_1_32_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). https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463030"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 1614-1623","author":"Martins Andre","year":"2016","unstructured":"Andre Martins and Ramon Astudillo. 2016. From softmax to sparsemax: A sparse model of attention and multi-label classification. In International conference on machine learning. PMLR, 1614-1623."},{"key":"e_1_3_2_1_36_1","volume-title":"Surveys in Combinatorics.","author":"McDiarmid Colin","unstructured":"Colin McDiarmid. 1989. On the Method of Bounded Differences. In Surveys in Combinatorics. Vol. 141. Cambridge University Press, 148-188."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.293"},{"key":"e_1_3_2_1_38_1","volume-title":"Foundations of Machine Learning (2 ed.)","author":"Mohri Mehryar","year":"2039","unstructured":"Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. 2018. Foundations of Machine Learning (2 ed.). MIT Press, Cambridge, MA. https:\/\/mitpress.mit.edu\/9780262039406\/foundations-of-machine-learning\/"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.conll-1.8"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730185"},{"key":"e_1_3_2_1_41_1","volume-title":"Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector. arXiv preprint arXiv:2510.00671","author":"Nguyen Thong","year":"2025","unstructured":"Thong Nguyen, Yibin Lei, Jia-Huei Ju, Eugene Yang, and Andrew Yates. 2025. Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector. arXiv preprint arXiv:2510.00671 (2025)."},{"key":"e_1_3_2_1_42_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. (November","author":"Nguyen Tri","year":"2016","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. (November 2016). https:\/\/www.microsoft.com\/en-us\/research\/publication\/ms-marco-human-generated-machine-reading-comprehension-dataset\/"},{"key":"e_1_3_2_1_43_1","volume-title":"Document expansion by query prediction. arXiv preprint arXiv:1904.08375","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Jimmy Lin, and Kyunghyun Cho. 2019. Document expansion by query prediction. arXiv preprint arXiv:1904.08375 (2019)."},{"key":"e_1_3_2_1_44_1","volume-title":"Ning Xu, Pradeep Ravikumar, and Barnab\u00e1s P\u00f3czos.","author":"Paria Biswajit","year":"2020","unstructured":"Biswajit Paria, Chih-Kuan Yeh, Ian EH Yen, Ning Xu, Pradeep Ravikumar, and Barnab\u00e1s P\u00f3czos. 2020. Minimizing flops to learn efficient sparse representations. arXiv preprint arXiv:2004.05665 (2020)."},{"key":"e_1_3_2_1_45_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Stephen E Robertson Steve Walker Susan Jones Micheline M Hancock-Beaulieu Mike Gatford et al. 1995. Okapi at TREC-3. British Library Research and Development Department.","DOI":"10.6028\/NIST.SP.500-225.city"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2572-2576","author":"Shen Xinjie","year":"2025","unstructured":"Xinjie Shen, Zhichao Geng, and Yang Yang. 2025. Exploring l0 Sparsification for Inference-free Sparse Retrievers. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2572-2576."},{"key":"e_1_3_2_1_52_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","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. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591902"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz et al. 2019. Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019).","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR). arXiv:2007","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 Proceedings of the 9th International Conference on Learning Representations (ICLR). arXiv:2007.00808."},{"key":"e_1_3_2_1_57_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint 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 preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462922"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:37:40Z","timestamp":1783694260000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809724"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":59,"alternative-id":["10.1145\/3805712.3809724","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809724","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}