{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:38:46Z","timestamp":1780637926803,"version":"3.54.1"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031424472","type":"print"},{"value":"9783031424489","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-42448-9_18","type":"book-chapter","created":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T23:02:21Z","timestamp":1694386941000},"page":"209-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Answer Retrieval for\u00a0Math Questions Using Structural and\u00a0Dense Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5387-0961","authenticated-orcid":false,"given":"Wei","family":"Zhong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9693-4892","authenticated-orcid":false,"given":"Yuqing","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7189","authenticated-orcid":false,"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,11]]},"reference":[{"key":"18_CR1","unstructured":"Bajaj, P., et al.: MS Marco: a human generated machine reading comprehension dataset (2016)"},{"key":"18_CR2","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"18_CR3","unstructured":"Bruch, S., Gai, S., Ingber, A.: An analysis of fusion functions for hybrid retrieval. arXiv:2210.11934 (2022)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Dai, Y., Chen, L., Zhang, Z.: An N-ary tree-based model for similarity evaluation on mathematical formulae. In: 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE (2020)","DOI":"10.1109\/SMC42975.2020.9283495"},{"key":"18_CR5","unstructured":"Dallas, F.: Math information retrieval using a text search engine. Master\u2019s thesis, University of Waterloo (2018)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Davila, K., Zanibbi, R.: Layout and semantics: combining representations for mathematical formula search. In: SIGIR (2017)","DOI":"10.1145\/3077136.3080748"},{"key":"18_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2019)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Fraser, D., Kane, A., Tompa, F.: Choosing math features for BM25 ranking with Tangent-L. In: DocEng (2018)","DOI":"10.1145\/3209280.3209527"},{"key":"18_CR9","unstructured":"Gao, L., Jiang, Z., Yin, Y., Yuan, K., Yan, Z., Tang, Z.: Preliminary exploration of formula embedding for mathematical information retrieval: can mathematical formulae be embedded like a natural language? arXiv:1707.05154 (2017)"},{"key":"18_CR10","unstructured":"Geletka, M., Kalivoda, V., \u0160tef\u00e1nik, M., Toma, M., Sojka, P.: Diverse semantics representation is King: MIRMU and MSM at ARQMath 2022. In: CLEF (2022)"},{"key":"18_CR11","unstructured":"Hagino, H., Saito, H.: Partial-match retrieval with structure-reflected indices at the NTCIR-10 math task. In: NTCIR. Citeseer (2013)"},{"key":"18_CR12","unstructured":"Hendrycks, D., et al.: Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874 (2021)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Hijikata, Y., Hashimoto, H., Nishida, S.: An investigation of index formats for the search of MathML objects. In: 2007 IEEE\/WIC\/ACM International Conferences on Web Intelligence and Intelligent Agent Technology-Workshops (2007)","DOI":"10.1109\/WIIATW.2007.4427581"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Hijikata, Y., Hashimoto, H., Nishida, S.: Search mathematical formulas by mathematical formulas. In: SHI (Symposium on Human Interface) (2009)","DOI":"10.1007\/978-3-642-02556-3_46"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: TinyBERT: distilling BERT for natural language understanding (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"18_CR16","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7, 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"18_CR17","unstructured":"Kane, A., Ng, Y.K., Tompa, F.: Dowsing for answers to math questions. Doing better with less. In: CLEF (2022)"},{"key":"18_CR18","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: SIGIR (2020)","DOI":"10.1145\/3397271.3401075"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Lee, K., Chang, M.W., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering. arXiv:1906.00300 (2019)","DOI":"10.18653\/v1\/P19-1612"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Lin, J.: A proposed conceptual framework for a representational approach to information retrieval (2021)","DOI":"10.1145\/3527546.3527552"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Lu, P., Qiu, L., Yu, W., Welleck, S., Chang, K.W.: A survey of deep learning for mathematical reasoning. arXiv preprint arXiv:2212.10535 (2022)","DOI":"10.18653\/v1\/2023.acl-long.817"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Lv, Y., Zhai, C.: Lower-bounding term frequency normalization. In: CIKM (2011)","DOI":"10.1145\/2063576.2063584"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Mansouri, B., Agarwal, A., Oard, D., Zanibbi, R.: Finding old answers to new math questions: the ARQMath Lab at CLEF 2020. In: Jose, J.M., et al. (eds.) Advances in Information Retrieval (2020)","DOI":"10.1007\/978-3-030-45442-5_73"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Mansouri, B., Novotn\u00fd, V., Agarwal, A., Oard, D.W., Zanibbi, R.: Overview of ARQMath-3 (2022): third CLEF lab on answer retrieval for questions on math (working notes version). In: Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum (2022)","DOI":"10.1007\/978-3-031-13643-6_20"},{"key":"18_CR26","unstructured":"Mansouri, B., Oard, D.W., Zanibbi, R.: DPRL systems in the CLEF 2020 ARQMath lab. In: CLEF (2020)"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Mansouri, B., Oard, D.W., Zanibbi, R.: DPRL systems in the CLEF 2021 ARQMath lab: sentence-BERT for answer retrieval, learning-to-rank for formula retrieval. In: CLEF (2021)","DOI":"10.1145\/3404835.3462956"},{"key":"18_CR28","unstructured":"Mansouri, B., Oard, D.W., Zanibbi, R.: DPRL systems in the CLEF 2022 ARQMath lab: introducing MathAMR for math-aware search. In: CLEF (2021)"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Mansouri, B., Rohatgi, S., Oard, D.W., Wu, J., Giles, C.L., Zanibbi, R.: Tangent-CFT: an embedding model for mathematical formulas. In: SIGIR (2019)","DOI":"10.1145\/3341981.3344235"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Mansouri, B., Zanibbi, R., Oard, D.W., Agarwal, A.: Overview of ARQMath-2 (2021): second CLEF lab on answer retrieval for questions on math (working notes version). In: Working Notes of CLEF 2021 - Conference and Labs of the Evaluation Forum (2021)","DOI":"10.1007\/978-3-030-85251-1_17"},{"key":"18_CR31","unstructured":"Miller, B.R., Youssef, A.: Technical aspects of the digital library of mathematical functions. In: AMAI (2003)"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Ng, Y.K.: Dowsing for math answers: exploring MathCQA with a math-aware search engine. Master\u2019s thesis, University of Waterloo (2021)","DOI":"10.1007\/978-3-030-85251-1_16"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Ng, Y.K., Fraser, D., Kassaie, B., Tompa, F.: Dowsing for answers to math questions: ongoing viability of traditional MathIR. In: CLEF (2021)","DOI":"10.1007\/978-3-030-85251-1_16"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Ng, Y.K., et al.: Dowsing for math answers with Tangent-L. In: CLEF (2020)","DOI":"10.1007\/978-3-030-85251-1_16"},{"key":"18_CR35","unstructured":"Nogueira, R., Jiang, Z., Lin, J.: Investigating the limitations of transformers with simple arithmetic tasks. arXiv:2102.13019 (2021)"},{"key":"18_CR36","unstructured":"Novotn\u1ef3, V., Sojka, P., Stef\u00e1nik, M., Lupt\u00e1k, D.: Three is better than one: ensembling math information retrieval systems. In: CLEF (2020)"},{"key":"18_CR37","unstructured":"Novotn\u1ef3, V., \u0160tef\u00e1nik, M.: Combining sparse and dense information retrieval. In: CLEF (2022)"},{"key":"18_CR38","unstructured":"Novotn\u1ef3, V., \u0160tef\u00e1nik, M., Lupt\u00e1k, D., Geletka, M., Zelina, P., Sojka, P.: Ensembling ten math information retrieval systems. In: CLEF (2021)"},{"key":"18_CR39","unstructured":"Pattaniyil, N., Zanibbi, R.: Combining TF-IDF text retrieval with an inverted index over symbol pairs in math expressions: the Tangent math search engine at NTCIR 2014. In: NTCIR (2014)"},{"key":"18_CR40","unstructured":"Peng, S., Yuan, K., Gao, L., Tang, Z.: MathBERT: a pre-trained model for mathematical formula understanding. arXiv:2105.00377 (2021)"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Porter, M.F.: An algorithm for suffix stripping. Program (1980)","DOI":"10.1108\/eb046814"},{"key":"18_CR42","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI blog (2019). https:\/\/openai.com\/blog\/better-language-models\/"},{"key":"18_CR43","unstructured":"Rae, J.W., et al.: Scaling language models: methods, analysis & insights from training gopher. arXiv:2112.11446 (2021)"},{"key":"18_CR44","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. arXiv:1908.10084 (2022)"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Reusch, A., Thiele, M., Lehner, W.: An ALBERT-based similarity measure for mathematical answer retrieval. In: SIGIR (2021)","DOI":"10.1145\/3404835.3463023"},{"key":"18_CR46","unstructured":"Reusch, A., Thiele, M., Lehner, W.: TU_DBS in the ARQMath lab 2021, CLEF. In: CLEF (2021)"},{"key":"18_CR47","unstructured":"Reusch, A., Thiele, M., Lehner, W.: Transformer-encoder and decoder models for questions on math. In: CLEF (2022)"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Schellenberg, T., Yuan, B., Zanibbi, R.: Layout-based substitution tree indexing and retrieval for mathematical expressions. In: DRR (2012)","DOI":"10.1117\/12.912502"},{"key":"18_CR49","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Z., Lan, A.S., Baraniuk, R.G.: Mathematical formula representation via tree embeddings. In: iTextbooks@ AIED (2021)","DOI":"10.1109\/BigData52589.2021.9671942"},{"key":"18_CR51","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: EMNLP (2020)"},{"key":"18_CR52","unstructured":"Yokoi, K., Aizawa, A.: An approach to similarity search for mathematical expressions using MathML. In: DML (Digital Mathematics Library) (2009)"},{"key":"18_CR53","unstructured":"Zanibbi, R., Aizawa, A., Kohlhase, M., Ounis, I., Topic, G., Davila, K.: NTCIR-12 MathIR task overview. In: NTCIR (2016)"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Zanibbi, R., Blostein, D.: Recognition and retrieval of mathematical expressions. In: IJDAR (2012)","DOI":"10.1117\/12.873312"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Zanibbi, R., Davila, K., Kane, A., Tompa, F.: The Tangent search engine: improved similarity metrics and scalability for math formula search. arXiv:1507.06235 (2015)","DOI":"10.1145\/2911451.2911512"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Zanibbi, R., Davila, K., Kane, A., Tompa, F.: Multi-stage math formula search: using appearance-based similarity metrics at scale. In: SIGIR (2016)","DOI":"10.1145\/2911451.2911512"},{"key":"18_CR57","unstructured":"Zhong, W.: A novel similarity-search method for mathematical content in LaTeX markup and its implementation. Ph.D. thesis, University of Delaware (2015)"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Zhong, W., Lin, J.: PyA0: a Python toolkit for accessible math-aware search. In: SIGIR (2021)","DOI":"10.1145\/3404835.3462794"},{"key":"18_CR59","doi-asserted-by":"crossref","unstructured":"Zhong, W., Lin, S.C., Yang, J.H., Lin, J.: One blade for one purpose: advancing math information retrieval using hybrid search. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (2023)","DOI":"10.1145\/3539618.3591746"},{"key":"18_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1007\/978-3-030-45439-5_47","volume-title":"Advances in Information Retrieval","author":"W Zhong","year":"2020","unstructured":"Zhong, W., Rohatgi, S., Wu, J., Giles, C.L., Zanibbi, R.: Accelerating substructure similarity search for formula retrieval. In: Jose, J.M., et al. (eds.) ECIR 2020. LNCS, vol. 12035, pp. 714\u2013727. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-45439-5_47"},{"key":"18_CR61","unstructured":"Zhong, W., Xie, Y., Lin, J.: Applying structural and dense semantic matching for the ARQMath lab 2022, CLEF. In: CLEF (2022)"},{"key":"18_CR62","doi-asserted-by":"crossref","unstructured":"Zhong, W., Yang, J.H., Lin, J.: Evaluating token-level and passage-level dense retrieval models for math information retrieval (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.78"},{"key":"18_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1007\/978-3-030-15712-8_8","volume-title":"Advances in Information Retrieval","author":"W Zhong","year":"2019","unstructured":"Zhong, W., Zanibbi, R.: Structural similarity search for formulas using leaf-root paths in operator subtrees. In: Azzopardi, L., Stein, B., Fuhr, N., Mayr, P., Hauff, C., Hiemstra, D. (eds.) ECIR 2019. LNCS, vol. 11437, pp. 116\u2013129. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-15712-8_8"},{"key":"18_CR64","unstructured":"Zhong, W., Zhang, X., Xin, J., Lin, J., Zanibbi, R.: Approach Zero and Anserini at the CLEF-2021 ARQMath track: applying substructure search and BM25 on operator tree path tokens. In: CLEF (2021)"}],"container-title":["Lecture Notes in Computer Science","Experimental IR Meets Multilinguality, Multimodality, and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42448-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:25:01Z","timestamp":1710260701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42448-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031424472","9783031424489"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42448-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"11 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CLEF","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Cross-Language Evaluation Forum for European Languages","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"clef2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clef2023.clef-initiative.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"29% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7 Best of 2022 Labs + 13 Lab Overviews","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}