{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T19:05:41Z","timestamp":1789153541112,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":83,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"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"}]},{"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":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591746","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"141-151","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["One Blade for One Purpose: Advancing Math Information Retrieval using Hybrid Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5387-0961","authenticated-orcid":false,"given":"Wei","family":"Zhong","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7989-9703","authenticated-orcid":false,"given":"Sheng-Chieh","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5469-312X","authenticated-orcid":false,"given":"Jheng-Hong","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7189","authenticated-orcid":false,"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Sebastian Bruch Siyu Gai and Amir Ingber. 2022. An analysis of fusion functions for hybrid retrieval. (2022). arxiv: 2210.11934"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Chris Buckley and Ellen M Voorhees. 2004. Retrieval evaluation with incomplete information. In SIGIR.","DOI":"10.1145\/1008992.1009000"},{"key":"e_1_3_2_2_3_1","volume-title":"Pre-training tasks for embedding-based large-scale retrieval. (2020). arxiv","author":"Chang Wei-Cheng","year":"2002","unstructured":"Wei-Cheng Chang, Felix X Yu, Yin-Wen Chang, Yiming Yang, and Sanjiv Kumar. 2020. Pre-training tasks for embedding-based large-scale retrieval. (2020). arxiv: 2002.03932"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC42975.2020.9283495"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Kenny Davila and Richard Zanibbi. 2017. Layout and semantics: Combining representations for mathematical formula search. In SIGIR.","DOI":"10.1145\/3077136.3080748"},{"key":"e_1_3_2_2_6_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.","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. (2019). arxiv: 1810.04805"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Thibault Formal Carlos Lassance Benjamin Piwowarski and St\u00e9phane Clinchant. 2021a. SPLADE v2: Sparse lexical and expansion model for information retrieval. (2021). arxiv: 2109.10086","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_2_8_1","volume-title":"SPLADE: Sparse lexical and expansion model for first stage ranking.","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021b. SPLADE: Sparse lexical and expansion model for first stage ranking. (2021). arxiv: 2107.05720"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Dallas Fraser Andrew Kane and Frank Tompa. 2018. Choosing math features for BM25 ranking with Tangent-L. In DocEng.","DOI":"10.1145\/3209280.3209527"},{"key":"e_1_3_2_2_10_1","volume-title":"Condenser: A pre-training architecture for dense retrieval.","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao and Jamie Callan. 2021a. Condenser: A pre-training architecture for dense retrieval. (2021). arxiv: 2104.08253"},{"key":"e_1_3_2_2_11_1","unstructured":"Luyu Gao and Jamie Callan. 2021b. Unsupervised corpus aware language model pre-training for dense passage retrieval. (2021). arxiv: 2108.05540"},{"key":"e_1_3_2_2_12_1","volume-title":"Preliminary exploration of formula embedding for mathematical information retrieval: Can mathematical formulae be embedded like a natural language?","author":"Gao Liangcai","year":"2017","unstructured":"Liangcai Gao, Zhuoren Jiang, Yue Yin, Ke Yuan, Zuoyu Yan, and Zhi Tang. 2017. Preliminary exploration of formula embedding for mathematical information retrieval: Can mathematical formulae be embedded like a natural language? (2017). arxiv: 1707.05154"},{"key":"e_1_3_2_2_13_1","unstructured":"Liangcai Gao Ke Yuan Yuehan Wang Zhuoren Jiang and Zhi Tang. 2016. The math retrieval system of ICST for NTCIR-12 MathIR Task. In NTCIR."},{"key":"e_1_3_2_2_14_1","volume-title":"Diverse semantics representation is king: MIRMU and MSM at ARQMath","author":"Geletka Martin","year":"2022","unstructured":"Martin Geletka, Vojt?ch Kalivoda, Michal ?tef\u00e1nik, Marek Toma, and Petr Sojka. 2022. Diverse semantics representation is king: MIRMU and MSM at ARQMath 2022. In CLEF."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Yoshinori Hijikata Hideki Hashimoto and Shogo Nishida. 2009. Search mathematical formulas by mathematical formulas. In SHI (Symposium on Human Interface).","DOI":"10.1007\/978-3-642-02556-3_46"},{"key":"e_1_3_2_2_16_1","volume-title":"Baker","author":"Hu Xuan","year":"2013","unstructured":"Xuan Hu, Liangcai Gao, Xiao-Rong Lin, Zhi Tang, Xiaofan Lin, and Josef B. Baker. 2013. WikiMirs: A mathematical information retrieval system for wikipedia. In JCDL."},{"key":"e_1_3_2_2_17_1","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. (2021). arxiv: 2112.09118"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_19_1","volume-title":"Yin Ki Ng, and Frank Tompa","author":"Kane Andrew","year":"2022","unstructured":"Andrew Kane, Yin Ki Ng, and Frank Tompa. 2022. Dowsing for answers to math questions. Doing better with less. CLEF (2022)."},{"key":"e_1_3_2_2_20_1","volume-title":"Dense passage retrieval for open-domain question answering. (2020). arxiv","author":"Karpukhin Vladimir","year":"2004","unstructured":"Vladimir Karpukhin, Barlas O\u011fuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. (2020). arxiv: 2004.04906"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and effective passage search via contextualized late interaction over BERT. In SIGIR.","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_2_22_1","unstructured":"Giovanni Yoko Kristianto Goran Topic and Akiko Aizawa. 2016. MCAT math retrieval system for NTCIR-12 MathIR task. In NTCIR."},{"key":"e_1_3_2_2_23_1","volume-title":"Equation embeddings. (2018). arxiv","author":"Krstovski Kriste","year":"1803","unstructured":"Kriste Krstovski and David M Blei. 2018. Equation embeddings. (2018). arxiv: 1803.09123"},{"key":"e_1_3_2_2_24_1","volume-title":"ALBERT: A lite BERT for self-supervised learning of language representations. arxiv","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. ALBERT: A lite BERT for self-supervised learning of language representations. arxiv: 1909.11942"},{"key":"e_1_3_2_2_25_1","volume-title":"Latent retrieval for weakly supervised open domain question answering. (2019). arxiv","author":"Lee Kenton","year":"1906","unstructured":"Kenton Lee, Ming-Wei Chang, and Kristina Toutanova. 2019. Latent retrieval for weakly supervised open domain question answering. (2019). arxiv: 1906.00300"},{"key":"e_1_3_2_2_26_1","unstructured":"Minghan Li and Eric Gaussier. 2022. Domain adaptation for dense retrieval through self-supervision by pseudo-relevance labeling. (2022). arxiv: 2212.06552"},{"key":"e_1_3_2_2_27_1","unstructured":"Jimmy Lin. 2021. A proposed conceptual framework for a representational approach to information retrieval. arxiv: 2110.01529"},{"key":"e_1_3_2_2_28_1","unstructured":"Sheng-Chieh Lin and Jimmy Lin. 2021. Densifying sparse representations for passage retrieval by representational slicing. (2021). arxiv: 2112.04666"},{"key":"e_1_3_2_2_29_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. (2017). arxiv: 1711.05101"},{"key":"e_1_3_2_2_30_1","unstructured":"Shuqi Lu Di He Chenyan Xiong Guolin Ke Waleed Malik Zhicheng Dou Paul Bennett Tieyan Liu and Arnold Overwijk. 2021. Less is more: Pre-train a strong text encoder for dense retrieval using a weak decoder. (2021). arxiv: 2102.09206"},{"key":"e_1_3_2_2_31_1","unstructured":"Yuanhua Lv and ChengXiang Zhai. 2011. Lower-bounding term frequency normalization. In CIKM."},{"key":"e_1_3_2_2_32_1","unstructured":"Xinyu Ma Jiafeng Guo Ruqing Zhang Yixing Fan and Xueqi Cheng. 2022. Pre-train a discriminative text encoder for dense retrieval via contrastive span prediction. (2022). arxiv: 2204.10641"},{"key":"e_1_3_2_2_33_1","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. (2021). arxiv: 2110.11540"},{"key":"e_1_3_2_2_34_1","volume-title":"Efficient Document-at-a-Time and Score-at-a-Time Query Evaluation for Learned Sparse Representations. ACM TOIS","author":"Mackenzie Joel","year":"2023","unstructured":"Joel Mackenzie, Andrew Trotman, and Jimmy Lin. 2023. Efficient Document-at-a-Time and Score-at-a-Time Query Evaluation for Learned Sparse Representations. ACM TOIS (2023)."},{"key":"e_1_3_2_2_35_1","unstructured":"Yu. A. Malkov and D. A. Yashunin. 2018. Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs. arxiv: 1603.09320"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Antonio Mallia Joel Mackenzie Torsten Suel and Nicola Tonellotto. 2022. Faster learned sparse retrieval with guided traversal. (2022). arxiv: 2204.11314","DOI":"10.1145\/3477495.3531774"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Behrooz Mansouri V\u00edt Novotn\u00fd Anurag Agarwal Douglas W. Oard and Richard Zanibbi. 2022. Overview of ARQMath-3 (2022): Third CLEF lab on Answer Retrieval for questions on math (working notes version). In CLEF.","DOI":"10.1007\/978-3-031-13643-6_20"},{"key":"e_1_3_2_2_38_1","volume-title":"DPRL systems in the CLEF 2022 ARQMath Lab: Introducing MathAMR for math-aware search. CLEF","author":"Mansouri Behrooz","year":"2021","unstructured":"Behrooz Mansouri, Douglas W Oard, and Richard Zanibbi. 2021a. DPRL systems in the CLEF 2022 ARQMath Lab: Introducing MathAMR for math-aware search. CLEF (2021)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Behrooz Mansouri Shaurya Rohatgi Douglas W. Oard Jian Wu C Lee Giles and Richard Zanibbi. 2019. Tangent-CFT: An embedding model for mathematical formulas. In SIGIR.","DOI":"10.1145\/3341981.3344235"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Behrooz Mansouri Richard Zanibbi Douglas W. Oard and Anurag Agarwal. 2021b. Overview of ARQMath-2 (2021): Second CLEF Lab on answer retrieval for questions on math (working notes version). In CLEF.","DOI":"10.1007\/978-3-030-85251-1_17"},{"key":"e_1_3_2_2_41_1","volume-title":"Miller and Abdou Youssef","author":"Bruce","year":"2003","unstructured":"Bruce R. Miller and Abdou Youssef. 2003. Technical aspects of the digital library of mathematical functions. In AMAI."},{"key":"e_1_3_2_2_42_1","unstructured":"Yin Ki Ng Dallas Fraser Besat Kassaie and Frank Tompa. 2021. Dowsing for answers to math questions: Ongoing viability of traditional MathIR. In CLEF."},{"key":"e_1_3_2_2_43_1","unstructured":"Yin Ki Ng Dallas J. Fraser Besat Kassaie George Labahn Mirette S Marzouk Frank Tompa and Kevin Wang. 2020. Dowsing for math answers with Tangent-L. In CLEF."},{"key":"e_1_3_2_2_44_1","unstructured":"Rodrigo Nogueira Zhiying Jiang and Jimmy Lin. 2021. Investigating the limitations of transformers with simple arithmetic tasks. (2021). arxiv: 2102.13019"},{"key":"e_1_3_2_2_45_1","volume-title":"Combining sparse and dense information retrieval. CLEF","author":"Novotn\u1ef3 V\u00edt","year":"2022","unstructured":"V\u00edt Novotn\u1ef3 and Michal \u0160tef\u00e1nik. 2022. Combining sparse and dense information retrieval. CLEF (2022)."},{"key":"e_1_3_2_2_46_1","unstructured":"V\u00edt Novotn\u1ef3 Michal \u0160tef\u00e1nik D\u00e1vid Lupt\u00e1k Martin Geletka Petr Zelina and Petr Sojka. 2021. Ensembling Ten Math Information Retrieval Systems In CLEF."},{"key":"e_1_3_2_2_47_1","unstructured":"Shuai Peng Ke Yuan Liangcai Gao and Zhi Tang. 2021. MathBERT: A pre-trained model for mathematical formula understanding. (2021). arxiv: 2105.00377"},{"key":"e_1_3_2_2_48_1","unstructured":"Lukas Pfahler and Katharina Morik. 2022. Self-Supervised Pretraining of Graph Neural Network for the Retrieval of Related Mathematical Expressions in Scientific Articles. (2022). arxiv: 2209.00446"},{"key":"e_1_3_2_2_49_1","volume-title":"An algorithm for suffix stripping. Program","author":"Porter Martin F","year":"1980","unstructured":"Martin F Porter. 1980. An algorithm for suffix stripping. Program (1980)."},{"key":"e_1_3_2_2_50_1","unstructured":"I Qunis G Amati V Plachouras B He C Macdonald and C Lioma. 2006. A high performance and scalable information retrieval plateform. In SIGR."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Ori Ram Gal Shachaf Omer Levy Jonathan Berant and Amir Globerson. 2021. Learning to retrieve passages without supervision. (2021). arxiv: 2112.07708","DOI":"10.18653\/v1\/2022.naacl-main.193"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Anja Reusch Maik Thiele and Wolfgang Lehner. 2021a. An ALBERT-based similarity measure for mathematical answer retrieval. In SIGIR.","DOI":"10.1145\/3404835.3463023"},{"key":"e_1_3_2_2_53_1","unstructured":"Anja Reusch Maik Thiele and Wolfgang Lehner. 2021b. TU_DBS in the ARQMath Lab 2021 CLEF. In CLEF."},{"key":"e_1_3_2_2_54_1","volume-title":"Transformer-encoder and decoder models for questions on math. CLEF","author":"Reusch Anja","year":"2022","unstructured":"Anja Reusch, Maik Thiele, and Wolfgang Lehner. 2022. Transformer-encoder and decoder models for questions on math. CLEF (2022)."},{"key":"e_1_3_2_2_55_1","volume-title":"On information retrieval metrics designed for evaluation with incomplete relevance assessments. Information Retrieval","author":"Sakai Tetsuya","year":"2008","unstructured":"Tetsuya Sakai and Noriko Kando. 2008. On information retrieval metrics designed for evaluation with incomplete relevance assessments. Information Retrieval (2008)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557325"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Keshav Santhanam Omar Khattab Jon Saad-Falcon Christopher Potts and Matei Zaharia. 2021. ColBERTv2: Effective and efficient retrieval via lightweight late interaction. (2021). arxiv: 2112.01488","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_2_58_1","volume-title":"Salim Roukos, Matei Zaharia, and Christopher Potts.","author":"Santhanam Keshav","year":"2022","unstructured":"Keshav Santhanam, Jon Saad-Falcon, Martin Franz, Omar Khattab, Avirup Sil, Radu Florian, Md Arafat Sultan, Salim Roukos, Matei Zaharia, and Christopher Potts. 2022b. Moving beyond downstream task accuracy for information retrieval benchmarking. (2022). arxiv: 2212.01340"},{"key":"e_1_3_2_2_59_1","volume-title":"A generalized weisfeiler-lehman graph kernel. Machine Learning","author":"Schulz Till Hendrik","year":"2022","unstructured":"Till Hendrik Schulz, Tam\u00e1s Horv\u00e1th, Pascal Welke, and Stefan Wrobel. 2022. A generalized weisfeiler-lehman graph kernel. Machine Learning (2022)."},{"key":"e_1_3_2_2_60_1","unstructured":"Tao Shen Xiubo Geng Chongyang Tao Can Xu Kai Zhang and Daxin Jiang. 2022. UnifieR: A Unified Retriever for Large-Scale Retrieval. (2022). arxiv: 2205.11194"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"crossref","unstructured":"Yujin Song and Xiaoyu Chen. 2021. Searching for mathematical formulas based on graph representation learning. In CICM.","DOI":"10.1007\/978-3-030-81097-9_11"},{"key":"e_1_3_2_2_62_1","unstructured":"Terrier contributors. 2014. Terrier documenetation. http:\/\/terrier.org\/docs\/v4.0\/javadoc\/org\/terrier\/matching\/models\/TF_IDF.html [Online; accessed 2022-12-17]."},{"key":"e_1_3_2_2_63_1","unstructured":"Nandan Thakur Nils Reimers and Jimmy Lin. 2022. Domain adaptation for memory-efficient dense retrieval. (2022). arxiv: 2205.11498"},{"key":"e_1_3_2_2_64_1","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 NIPS."},{"key":"e_1_3_2_2_65_1","volume-title":"GPL: Generative pseudo labeling for unsupervised domain adaptation of dense retrieval.","author":"Wang Kexin","year":"2021","unstructured":"Kexin Wang, Nandan Thakur, Nils Reimers, and Iryna Gurevych. 2021a. GPL: Generative pseudo labeling for unsupervised domain adaptation of dense retrieval. (2021). arxiv: 2112.07577"},{"key":"e_1_3_2_2_66_1","volume-title":"2021 IEEE International Conference on Big Data.","author":"Wang Zichao","unstructured":"Zichao Wang, Mengxue Zhang, Richard G. Baraniuk, and Andrew S. Lan. 2021b. Scientific Formula Retrieval via Tree Embeddings. In 2021 IEEE International Conference on Big Data."},{"key":"e_1_3_2_2_67_1","volume-title":"Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander Rush.","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In EMNLP."},{"key":"e_1_3_2_2_68_1","unstructured":"Xing Wu Guangyuan Ma Meng Lin Zijia Lin Zhongyuan Wang and Songlin Hu. 2022. Contextual mask auto-encoder for dense passage retrieval. (2022). arxiv: 2208.07670"},{"key":"e_1_3_2_2_69_1","volume-title":"How powerful are graph neural networks?","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? (2018). arxiv: 1810.00826"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080721"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"crossref","unstructured":"Michihiro Yasunaga and John D Lafferty. 2019. TopicEQ: A joint topic and mathematical equation model for scientific texts. In AAAI.","DOI":"10.1609\/aaai.v33i01.33017394"},{"key":"e_1_3_2_2_72_1","unstructured":"Richard Zanibbi Akiko Aizawa Michael Kohlhase Iadh Ounis Goran Topic and Kenny Davila. 2016a. NTCIR-12 MathIR task overview. In NTCIR."},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"crossref","unstructured":"Richard Zanibbi and Dorothea Blostein. 2012. Recognition and retrieval of mathematical expressions. In IJDAR.","DOI":"10.1117\/12.873312"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"crossref","unstructured":"Richard Zanibbi Kenny Davila Andrew Kane and Frank Tompa. 2016b. Multi-stage math formula search: Using appearance-based similarity metrics at scale. In SIGIR.","DOI":"10.1145\/2911451.2911512"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"crossref","unstructured":"Jingtao Zhan Jiaxin Mao Yiqun Liu Jiafeng Guo Min Zhang and Shaoping Ma. 2022. Learning discrete representations via constrained clustering for effective and efficient dense retrieval. In WSDM.","DOI":"10.1145\/3488560.3498443"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"crossref","unstructured":"Jin Zhao Min-Yen Kan and Yin Leng Theng. 2008. Math information retrieval: user requirements and prototype implementation. In JCDL.","DOI":"10.1145\/1378889.1378921"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"crossref","unstructured":"Wei Zhong and Jimmy Lin. 2021. PyA0: A Python toolkit for accessible math-aware search. In SIGIR.","DOI":"10.1145\/3404835.3462794"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"crossref","unstructured":"Wei Zhong Shaurya Rohatgi Jian Wu Lee Giles and Richard Zanibbi. 2020. Accelerating substructure similarity search for formula retrieval. In ECIR.","DOI":"10.1007\/978-3-030-45439-5_47"},{"key":"e_1_3_2_2_79_1","volume-title":"Applying structural and dense semantic matching for the ARQMath Lab","author":"Zhong Wei","year":"2022","unstructured":"Wei Zhong, Yuqing Xie, and Jimmy Lin. 2022a. Applying structural and dense semantic matching for the ARQMath Lab 2022, CLEF. CLEF (2022)."},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"crossref","unstructured":"Wei Zhong Jheng-Hong Yang and Jimmy Lin. 2022b. Evaluating token-level and passage-level dense retrieval models for math information retrieval. arxiv: 2203.11163","DOI":"10.18653\/v1\/2022.findings-emnlp.78"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"crossref","unstructured":"Wei Zhong and Richard Zanibbi. 2019. Structural similarity search for formulas using leaf-root paths in operator subtrees. In ECIR.","DOI":"10.1007\/978-3-030-15712-8_8"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"crossref","unstructured":"Qi Zhu Yuxian Gu Lingxiao Luo Bing Li Cheng Li Wei Peng Minlie Huang and Xiaoyan Zhu. 2021. When does further pre-training MLM help? An empirical study on task-oriented dialog pre-training. In EMNLP.","DOI":"10.18653\/v1\/2021.insights-1.9"},{"key":"e_1_3_2_2_83_1","unstructured":"Shengyao Zhuang and Guido Zuccon. 2021. Fast passage re-ranking with contextualized exact term matching and efficient passage expansion. (2021). arxiv: 2108.08513"}],"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\/3539618.3591746","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:01Z","timestamp":1750178821000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591746"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":83,"alternative-id":["10.1145\/3539618.3591746","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591746","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"}}]}}