{"id":"https://openalex.org/W6990780937","doi":null,"title":"Effective Math-Aware Ad-Hoc Retrieval based on Structure Search and Semantic Similarities","display_name":"Effective Math-Aware Ad-Hoc Retrieval based on Structure Search and Semantic Similarities","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W6990780937"},"language":"en","primary_location":{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/19865","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/19865","pdf_url":"https://uwspace.uwaterloo.ca/bitstreams/c00b92fd-51a5-4332-bfec-79c4f67637be/download","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://uwspace.uwaterloo.ca/bitstreams/c00b92fd-51a5-4332-bfec-79c4f67637be/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102024277","display_name":"Wei Zhong","orcid":"https://orcid.org/0009-0001-5387-0961","observed_orcids":["https://orcid.org/0009-0001-5387-0961"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhong, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5102024277"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9580000042915344,"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":0.9580000042915344,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.040800001472234726,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11269","display_name":"Algorithms and Data Compression","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/structural-similarity","display_name":"structural similarity","score":0.6830000281333923},{"id":"https://openalex.org/keywords/dynamic-pruning","display_name":"dynamic pruning","score":0.7540000081062317},{"id":"https://openalex.org/keywords/hybrid-search","display_name":"hybrid retrieval","score":0.7360000014305115},{"id":"https://openalex.org/keywords/unsupervised-retrieval","display_name":"unsupervised retrieval","score":0.6729999780654907},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8510000109672546},{"id":"https://openalex.org/keywords/scientific-information-retrieval","display_name":"scientific information retrieval","score":0.7639999985694885},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.49900001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6122000217437744},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.589900016784668},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.45399999618530273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4526999890804291},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.3986999988555908},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.39750000834465027},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.38920000195503235},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.34599998593330383},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33799999952316284},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2685000002384186},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C130327152","wikidata":"https://www.wikidata.org/wiki/Q748349","display_name":"Mathematical structure","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/19865","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/19865","pdf_url":"https://uwspace.uwaterloo.ca/bitstreams/c00b92fd-51a5-4332-bfec-79c4f67637be/download","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"}],"best_oa_location":{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/19865","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/19865","pdf_url":"https://uwspace.uwaterloo.ca/bitstreams/c00b92fd-51a5-4332-bfec-79c4f67637be/download","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6990780937.pdf","grobid_xml":"https://content.openalex.org/works/W6990780937.grobid-xml"},"referenced_works_count":142,"referenced_works":["https://openalex.org/W1664191947","https://openalex.org/W1692912648","https://openalex.org/W1904365287","https://openalex.org/W1965657003","https://openalex.org/W1973520416","https://openalex.org/W1980344365","https://openalex.org/W1984565341","https://openalex.org/W2004918107","https://openalex.org/W2005545412","https://openalex.org/W2031071334","https://openalex.org/W2043150166","https://openalex.org/W2054429798","https://openalex.org/W2061382457","https://openalex.org/W2072193005","https://openalex.org/W2082783986","https://openalex.org/W2109244020","https://openalex.org/W2118274478","https://openalex.org/W2123006679","https://openalex.org/W2126602081","https://openalex.org/W2133564696","https://openalex.org/W2136189984","https://openalex.org/W2144211451","https://openalex.org/W2151297513","https://openalex.org/W2152311353","https://openalex.org/W2154610494","https://openalex.org/W2162432120","https://openalex.org/W2162697159","https://openalex.org/W2338908902","https://openalex.org/W2340997632","https://openalex.org/W2341132943","https://openalex.org/W2486753540","https://openalex.org/W2516925101","https://openalex.org/W2536015822","https://openalex.org/W2597655663","https://openalex.org/W2610935556","https://openalex.org/W2648699835","https://openalex.org/W2737236965","https://openalex.org/W2740807107","https://openalex.org/W2783640434","https://openalex.org/W2795454886","https://openalex.org/W2894175714","https://openalex.org/W2894175828","https://openalex.org/W2895358146","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2908510526","https://openalex.org/W2909544278","https://openalex.org/W2916588339","https://openalex.org/W2937036051","https://openalex.org/W2940927814","https://openalex.org/W2947497897","https://openalex.org/W2949335953","https://openalex.org/W2951534261","https://openalex.org/W2964199361","https://openalex.org/W2965373594","https://openalex.org/W2969574947","https://openalex.org/W2975059944","https://openalex.org/W2975239981","https://openalex.org/W2982596739","https://openalex.org/W2995273672","https://openalex.org/W2996064239","https://openalex.org/W3001279689","https://openalex.org/W3007672467","https://openalex.org/W3015883388","https://openalex.org/W3017961061","https://openalex.org/W3021397474","https://openalex.org/W3022373106","https://openalex.org/W3023176652","https://openalex.org/W3033187248","https://openalex.org/W3034912391","https://openalex.org/W3037128914","https://openalex.org/W3037932933","https://openalex.org/W3038572442","https://openalex.org/W3039017601","https://openalex.org/W3090721331","https://openalex.org/W3093570284","https://openalex.org/W3094064346","https://openalex.org/W3105966348","https://openalex.org/W3117576675","https://openalex.org/W3125917269","https://openalex.org/W3133029875","https://openalex.org/W3154755316","https://openalex.org/W3155519060","https://openalex.org/W3155895380","https://openalex.org/W3156636935","https://openalex.org/W3156794988","https://openalex.org/W3157133882","https://openalex.org/W3158196282","https://openalex.org/W3168875417","https://openalex.org/W3170739233","https://openalex.org/W3174203100","https://openalex.org/W3177654787","https://openalex.org/W3185250692","https://openalex.org/W3188983256","https://openalex.org/W3193367516","https://openalex.org/W3199842874","https://openalex.org/W3200910169","https://openalex.org/W3203502727","https://openalex.org/W3206003720","https://openalex.org/W3209946909","https://openalex.org/W3211633257","https://openalex.org/W3214825504","https://openalex.org/W4224865658","https://openalex.org/W4226146865","https://openalex.org/W4226443693","https://openalex.org/W4226518707","https://openalex.org/W4233135949","https://openalex.org/W4234071252","https://openalex.org/W4246183800","https://openalex.org/W4281493120","https://openalex.org/W4284664419","https://openalex.org/W4284880643","https://openalex.org/W4286242951","https://openalex.org/W4294437823","https://openalex.org/W4301194718","https://openalex.org/W4303684020","https://openalex.org/W4304195432","https://openalex.org/W4306317212","https://openalex.org/W4309209230","https://openalex.org/W4310746846","https://openalex.org/W4313304293","https://openalex.org/W4313304472","https://openalex.org/W4318718936","https://openalex.org/W4318751294","https://openalex.org/W4319996463","https://openalex.org/W4320813768","https://openalex.org/W4323572061","https://openalex.org/W4377138005","https://openalex.org/W4382239620","https://openalex.org/W4385567664","https://openalex.org/W4385570391","https://openalex.org/W4385571915","https://openalex.org/W4385573970","https://openalex.org/W4386902358","https://openalex.org/W4401042773","https://openalex.org/W4415795271","https://openalex.org/W7133199696","https://openalex.org/W7133202489","https://openalex.org/W7133211296","https://openalex.org/W7133214447","https://openalex.org/W7133217858","https://openalex.org/W7133230468"],"related_works":["https://openalex.org/W2319050966","https://openalex.org/W4409167607","https://openalex.org/W7039539207","https://openalex.org/W4386587212","https://openalex.org/W1620710625","https://openalex.org/W3016200987","https://openalex.org/W6948530631","https://openalex.org/W2740807107","https://openalex.org/W4404818675","https://openalex.org/W4220987026"],"abstract_inverted_index":{"Despite":[0],"the":[1,10,35,106,117,144,190,206,217,310,365,383,393,395,401,432],"prevalence":[2],"of":[3,37,130,165,208,403,415,434],"digital":[4],"scientific":[5,31],"and":[6,23,41,44,62,147,159,161,224,244,285,323,370],"educational":[7],"contents":[8],"on":[9,97,143],"Internet,":[11],"only":[12],"a":[13,111,184,201,232,300,341,358],"few":[14],"search":[15,61,248],"engines":[16],"are":[17,242,255,333],"capable":[18],"to":[19,71,173,189,205,257,276,321,335,347,430],"retrieve":[20],"them":[21],"efficiently":[22,215],"effectively.":[24],"\\nThe":[25,121,134,211],"main":[26],"challenge":[27],"in":[28,110,313,340,351,406],"freely":[29],"searching":[30],"literature":[32],"arises":[33],"from":[34,386],"presence":[36],"structured":[38],"math":[39,315,353,369,421],"formulas":[40,95],"their":[42],"heterogeneous":[43,352],"contextually":[45],"important":[46],"surrounding":[47,372],"words.":[48],"\\nThis":[49,374],"thesis":[50,396],"introduces":[51],"an":[52,86],"effective":[53,349,378],"math-aware,":[54],"ad-hoc":[55],"retrieval":[56,88,213,282,317],"model":[57,89,178],"that":[58,90,230,329,362],"incorporates":[59],"structure":[60,82,98,122,132,136,174,197,209,228,304],"semantic":[63,292,338],"similarities.":[64],"\\nTransformer-based":[65],"neural":[66,297,331],"retrievers":[67,298,332],"have":[68,295,327,356],"been":[69,270,428],"adopted":[70],"capture":[72,290,336],"additional":[73,337],"semantics":[74],"using":[75,387],"domain-adapted":[76],"supervised":[77,330],"retrieval.":[78,210,423],"\\n":[79,193,288,391],"\\nTo":[80,194,235,289],"enable":[81],"search,":[83,198],"I":[84,199,294,326,355],"suggest":[85],"unsupervised":[87,177,324],"can":[91,139,363],"filter":[92],"potential":[93,227],"mathematical":[94],"based":[96,142],"similarity.":[99],"This":[100,272,306,409],"similarity":[101,137],"is":[102,124,274],"determined":[103],"by":[104,126],"measuring":[105],"largest":[107],"common":[108,166,219],"substructure(s)":[109],"formula":[112,222],"tree":[113],"representation,":[114],"known":[115],"as":[116,157],"Operator":[118],"Tree":[119],"(OPT).":[120],"matching":[123,129,186],"approximated":[125],"employing":[127],"maximum":[128,218],"path-based":[131],"features.":[133],"proposed":[135,212,256,357],"measurement":[138],"be":[140,277],"tailored":[141],"desired":[145],"effectiveness":[146,259,312],"efficiency":[148,384],"trade-offs.":[149],"It":[150],"may":[151],"consider":[152],"various":[153],"node":[154],"types,":[155],"such":[156],"operators":[158],"operands,":[160],"accommodate":[162],"different":[163],"numbers":[164],"subtrees":[167],"with":[168,260,279,303],"varying":[169],"weights.":[170],"In":[171,319],"addition":[172],"similarity,":[175],"this":[176],"also":[179],"captures":[180],"symbol":[181],"substitutions":[182],"through":[183],"greedy":[185],"algorithm":[187,204,214],"applied":[188],"matched":[191],"substructure(s).":[192],"achieve":[195],"efficient":[196],"introduce":[200],"dynamic":[202,233],"pruning":[203,240],"problem":[207],"identifies":[216],"subtree":[220],"among":[221],"candidates":[223],"safely":[225],"eliminates":[226],"matches":[229],"exceed":[231],"threshold.":[234],"accomplish":[236],"this,":[237],"three":[238],"rank-safe":[239],"strategies":[241],"suggested":[243],"compared":[245],"against":[246],"exhaustive":[247],"baselines.":[249],"Additionally,":[250],"more":[251],"aggressive":[252],"thresholding":[253],"policies":[254],"balance":[258],"further":[261],"speed":[262],"improvements.":[263],"\\nA":[264],"novel":[265,359],"hierarchical":[266],"inverted":[267],"index":[268,273],"has":[269,308,427],"implemented.":[271],"designed":[275],"compatible":[278],"traditional":[280],"information":[281,316,422],"(IR)":[283],"infrastructure":[284],"optimization":[286],"techniques.":[287],"other":[291],"similarities,":[293],"incorporated":[296],"into":[299],"hybrid":[301],"setting":[302],"search.":[305],"approach":[307],"achieved":[309],"state-of-the-art":[311],"recent":[314,404],"tasks.":[318],"comparison":[320],"strict":[322],"matching,":[325],"found":[328],"able":[334],"similarities":[339],"highly":[342],"complementary":[343],"manner.":[344],"\\nIn":[345,392],"order":[346],"learn":[348],"representations":[350],"contents,":[354],"pretraining":[360,375],"architecture":[361],"improve":[364],"contextual":[366],"awareness":[367],"between":[368],"its":[371],"texts.":[373],"scheme":[376],"generates":[377],"downstream":[379],"single-vector":[380],"representations,":[381],"eliminating":[382],"bottleneck":[385],"multi-vector":[388],"dense":[389],"representations.":[390],"end,":[394],"examines":[397],"future":[398],"directions,":[399],"specifically":[400],"integration":[402],"advancements":[405],"language":[407,417],"modeling.":[408],"includes":[410],"incorporating":[411],"ongoing":[412],"exciting":[413],"developments":[414],"large":[416],"models":[418],"for":[419],"improved":[420],"A":[424],"preliminary":[425],"evaluation":[426],"conducted":[429],"assess":[431],"impact":[433],"these":[435],"advancements.":[436]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}