{"id":"https://openalex.org/W4321791261","doi":"https://doi.org/10.1142/s0218194023500080","title":"Identifying Notable Tuples in Multi-Concept Web Tables","display_name":"Identifying Notable Tuples in Multi-Concept Web Tables","publication_year":2023,"publication_date":"2023-02-24","ids":{"openalex":"https://openalex.org/W4321791261","doi":"https://doi.org/10.1142/s0218194023500080"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194023500080","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s0218194023500080","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"},"type":"article","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/A5085559168","display_name":"Yihai Xi","orcid":"https://orcid.org/0000-0002-1268-0678"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihai Xi","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, P. R. China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100387096","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0001-8903-8790"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Wang","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, P. R. China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100387096"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02127057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"04","first_page":"575","last_page":"602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9972000122070312,"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/T11719","display_name":"Data Quality and Management","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.8774206638336182},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7365999221801758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7102357149124146},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6235964894294739},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5617750883102417},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4754961431026459},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46113288402557373},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29490935802459717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1978836953639984}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8774206638336182},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7365999221801758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102357149124146},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6235964894294739},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5617750883102417},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4754961431026459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46113288402557373},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29490935802459717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1978836953639984},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218194023500080","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s0218194023500080","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2627493351","display_name":null,"funder_award_id":"2018YFC0809800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1495062271","https://openalex.org/W1552847225","https://openalex.org/W1992479406","https://openalex.org/W2066636486","https://openalex.org/W2092364718","https://openalex.org/W2325227998","https://openalex.org/W2398606196","https://openalex.org/W2575118467","https://openalex.org/W2766820594","https://openalex.org/W2795163497","https://openalex.org/W2891515342","https://openalex.org/W2962873665"],"related_works":["https://openalex.org/W2093597205","https://openalex.org/W2389846579","https://openalex.org/W2392495745","https://openalex.org/W132250100","https://openalex.org/W2099984331","https://openalex.org/W2981651290","https://openalex.org/W1539478205","https://openalex.org/W2106813246","https://openalex.org/W2725657302","https://openalex.org/W1512698090"],"abstract_inverted_index":{"Identifying":[0],"notable":[1,26,69],"tuples":[2,27,70],"in":[3,28,57,71,104,144],"a":[4,43,72,78,95,135],"web":[5,29,34,74,156],"table":[6,12,15,35,75],"is":[7,152],"of":[8,42,67,138,141,149,173,189],"great":[9],"help":[10],"for":[11,24,32,121],"understanding":[13],"and":[14,76,89,102,118,125,129,178],"summarization.":[16],"However,":[17],"existing":[18],"document-internal":[19],"feature-based":[20],"methods":[21],"are":[22],"inappropriate":[23],"identifying":[25,68],"tables.":[30,157],"Additionally,":[31],"the":[33,39,65,105,145,165,171,182],"describing":[36],"multiple":[37,50,86,175],"concepts,":[38],"notability":[40,111,133,139],"evaluation":[41,148],"tuple":[44,132],"needs":[45],"to":[46],"take":[47],"into":[48],"account":[49],"entities":[51,143],"as":[52,54],"well":[53],"their":[55,90],"importance":[56,91],"this":[58,61],"tuple.":[59,146],"In":[60],"paper,":[62],"we":[63],"investigate":[64],"task":[66],"multi-concept":[73],"propose":[77],"framework":[79],"that":[80,161],"includes":[81],"three":[82],"tasks:":[83],"(1)":[84],"identify":[85],"entity":[87,110,115,122,126,176,191],"columns":[88,177],"weights":[92],"by":[93,134,168,179],"building":[94],"column":[96],"correlation":[97],"graph":[98,117],"based":[99,113,153],"on":[100,114,154,170,181],"types":[101],"relationships":[103],"table;":[106],"(2)":[107],"obtain":[108],"fine-grained":[109],"scores":[112,140],"link":[116,123],"provide":[119],"solution":[120],"failure":[124],"domain":[127],"neglection;":[128],"(3)":[130],"evaluate":[131],"weighted":[136],"sum":[137],"all":[142],"Comprehensive":[147],"our":[150,162],"approach":[151,163],"real-world":[155],"The":[158],"results":[159],"demonstrate":[160],"outperforms":[164],"state-of-the-art":[166],"baselines":[167],"4.6%":[169],"precision":[172],"detecting":[174],"12.5%":[180],"metric":[183],"normalized":[184],"discounted":[185],"cumulative":[186],"gain":[187],"(NDCG)":[188],"evaluating":[190],"notability.":[192]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}