{"id":"https://openalex.org/W4205451693","doi":"https://doi.org/10.1109/bigdata52589.2021.9671942","title":"Scientific Formula Retrieval via Tree Embeddings","display_name":"Scientific Formula Retrieval via Tree Embeddings","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205451693","doi":"https://doi.org/10.1109/bigdata52589.2021.9671942"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671942","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101521658","display_name":"Zichao Wang","orcid":"https://orcid.org/0000-0001-8346-7033"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zichao Wang","raw_affiliation_strings":["Dept. Electrical and Computer Engineering, Rice University, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Electrical and Computer Engineering, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101778063","display_name":"Mengxue Zhang","orcid":"https://orcid.org/0000-0002-0797-0881"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengxue Zhang","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072713767","display_name":"Richard G. Baraniuk","orcid":"https://orcid.org/0000-0002-0721-8999"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard G. Baraniuk","raw_affiliation_strings":["Dept. Electrical and Computer Engineering, Rice University, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Electrical and Computer Engineering, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063813962","display_name":"Andrew Lan","orcid":"https://orcid.org/0000-0002-8475-6600"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew S. Lan","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0241,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87707045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1493","last_page":"1503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9296000003814697,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6495341062545776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6070259213447571},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.551032304763794},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5429153442382812},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.5379254817962646},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.48006710410118103},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4375704824924469},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4206681549549103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36351582407951355},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34492555260658264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27832502126693726},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.1602390706539154},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.14604562520980835}],"concepts":[{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6495341062545776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6070259213447571},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.551032304763794},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5429153442382812},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.5379254817962646},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48006710410118103},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4375704824924469},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4206681549549103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36351582407951355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34492555260658264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27832502126693726},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.1602390706539154},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.14604562520980835},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671942","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1498238796","https://openalex.org/W1523019309","https://openalex.org/W1978413491","https://openalex.org/W2028509346","https://openalex.org/W2031071334","https://openalex.org/W2109244020","https://openalex.org/W2130942839","https://openalex.org/W2157331557","https://openalex.org/W2187089797","https://openalex.org/W2493109812","https://openalex.org/W2587741066","https://openalex.org/W2594866016","https://openalex.org/W2626873800","https://openalex.org/W2737236965","https://openalex.org/W2740807107","https://openalex.org/W2786865417","https://openalex.org/W2935550293","https://openalex.org/W2942465004","https://openalex.org/W2963133108","https://openalex.org/W2963355447","https://openalex.org/W2963676163","https://openalex.org/W2964003257","https://openalex.org/W2971270287","https://openalex.org/W2971351900","https://openalex.org/W2975239981","https://openalex.org/W2995359496","https://openalex.org/W2996840337","https://openalex.org/W3008282111","https://openalex.org/W3016200987","https://openalex.org/W3037556679","https://openalex.org/W3102516861","https://openalex.org/W3110350694","https://openalex.org/W3208188706","https://openalex.org/W4210984920","https://openalex.org/W4288376504","https://openalex.org/W4289373464","https://openalex.org/W6630027374","https://openalex.org/W6679436768","https://openalex.org/W6733974131","https://openalex.org/W6735020992","https://openalex.org/W6740017710","https://openalex.org/W6741682314","https://openalex.org/W6748774801","https://openalex.org/W6754880608","https://openalex.org/W6758604235","https://openalex.org/W6762265231","https://openalex.org/W6766951040","https://openalex.org/W6770166318","https://openalex.org/W6771313149","https://openalex.org/W6771324808","https://openalex.org/W6779372110","https://openalex.org/W6794620107"],"related_works":["https://openalex.org/W2355247546","https://openalex.org/W2227684440","https://openalex.org/W2376256808","https://openalex.org/W2379488605","https://openalex.org/W2889201838","https://openalex.org/W2968666469","https://openalex.org/W3034799230","https://openalex.org/W2792946098","https://openalex.org/W2491277646","https://openalex.org/W2484254769"],"abstract_inverted_index":{"Exploiting":[0],"the":[1,77,98,112,115],"ever-growing":[2],"corpus":[3],"of":[4,52,114],"scientific":[5,19,30,54,140],"content":[6],"calls":[7],"for":[8,27],"new":[9,24],"ways":[10],"and":[11,17,66,85,132],"means":[12],"to":[13,60],"effectively":[14],"organize,":[15],"search,":[16],"retrieve":[18],"formulae.":[20],"We":[21,101,119],"propose":[22],"a":[23,72,87,93,104,135],"data-driven":[25],"framework":[26],"retrieving":[28],"similar":[29],"formulae":[31,55,141],"via":[32,45],"learned":[33],"formula":[34,130],"representations":[35,51],"based":[36],"on":[37,129],"tree":[38,50,73,80,88,96,106],"embeddings.":[39],"FORTE":[40,69,122],"(for":[41],"FOrmula":[42],"Representation":[43],"learning":[44],"Tree":[46],"Embeddings)":[47],"leverages":[48],"operator":[49,79,95,117],"symbolic":[53],"(such":[56],"as":[57],"math":[58],"equations)":[59],"explicitly":[61],"capture":[62],"their":[63],"inherent":[64],"structural":[65],"semantic":[67],"properties.":[68],"employs":[70],"i)":[71],"encoder":[74],"that":[75,90,110,121],"encodes":[76],"formula\u2019s":[78,94],"into":[81],"an":[82],"embedding":[83,99],"vector":[84],"ii)":[86],"decoder":[89],"directly":[91],"generates":[92],"from":[97],"vector.":[100],"also":[102],"develop":[103],"novel":[105],"beam":[107],"search":[108],"algorithm":[109],"improves":[111],"quality":[113],"decoded":[116],"trees.":[118],"demonstrate":[120],"(sometimes":[123],"significantly)":[124],"outperforms":[125],"various":[126],"baseline":[127],"methods":[128],"reconstruction":[131],"retrieval":[133],"using":[134],"real-world":[136],"dataset":[137],"comprising":[138],"770k":[139],"collected":[142],"on-line.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}