{"id":"https://openalex.org/W3059331691","doi":"https://doi.org/10.1145/3340531.3412019","title":"Generating Categories for Sets of Entities","display_name":"Generating Categories for Sets of Entities","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3059331691","doi":"https://doi.org/10.1145/3340531.3412019","mag":"3059331691"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.08428","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shuo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Bloomberg, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bloomberg, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Krisztian Balog","orcid":null},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Krisztian Balog","raw_affiliation_strings":["University of Stavanger, Stavanger, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1833","last_page":"1842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9962999820709229,"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/automatic-summarization","display_name":"Automatic summarization","score":0.6876000165939331},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5325999855995178},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.49059998989105225},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.40860000252723694},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.36160001158714294},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.3515999913215637},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.34049999713897705},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.3357999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384999990463257},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6876000165939331},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5144000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975999891757965},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3340531.3412019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.08428","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.08428","pdf_url":"https://arxiv.org/pdf/2008.08428","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.08428","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.08428","pdf_url":"https://arxiv.org/pdf/2008.08428","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1982078690","https://openalex.org/W2020022499","https://openalex.org/W2020278455","https://openalex.org/W2032327522","https://openalex.org/W2034953016","https://openalex.org/W2046217376","https://openalex.org/W2087160028","https://openalex.org/W2091950909","https://openalex.org/W2104428806","https://openalex.org/W2116275525","https://openalex.org/W2150286230","https://openalex.org/W2339675141","https://openalex.org/W2341748398","https://openalex.org/W2564425030","https://openalex.org/W2579131192","https://openalex.org/W2584630532","https://openalex.org/W2740592503","https://openalex.org/W2789227036","https://openalex.org/W2893047995","https://openalex.org/W2946531303","https://openalex.org/W2962756504","https://openalex.org/W2962891712","https://openalex.org/W2962985882","https://openalex.org/W2971470875","https://openalex.org/W3004185181","https://openalex.org/W3008881932","https://openalex.org/W6600900695"],"related_works":[],"abstract_inverted_index":{"Category":[0],"systems":[1],"are":[2,21,91],"central":[3],"components":[4],"of":[5,14,34,46,56,61,106,124],"knowledge":[6,40],"bases,":[7],"as":[8],"they":[9],"provide":[10],"a":[11,22,31,48,54,113],"hierarchical":[12],"grouping":[13],"semantically":[15],"related":[16],"concepts":[17],"and":[18,24,88,109,120],"entities.":[19,62],"They":[20],"unique":[23],"valuable":[25],"resource":[26],"that":[27],"is":[28,80],"utilized":[29],"in":[30,42,104],"broad":[32],"range":[33],"information":[35],"access":[36],"tasks.":[37],"To":[38],"aid":[39],"editors":[41],"the":[43,75,78,99,122,125],"manual":[44],"process":[45],"expanding":[47],"category":[49],"system,":[50],"this":[51],"paper":[52],"presents":[53],"method":[55],"generating":[57],"categories":[58,119],"for":[59,82],"sets":[60],"First,":[63],"we":[64],"employ":[65],"neural":[66],"abstractive":[67],"summarization":[68],"models":[69],"to":[70,93,96],"generate":[71],"candidate":[72],"categories.":[73],"Next,":[74],"location":[76],"within":[77],"hierarchy":[79],"identified":[81],"each":[83],"candidate.":[84],"Finally,":[85],"structure-,":[86],"content-,":[87],"hierarchy-based":[89],"features":[90],"used":[92],"rank":[94],"candidates":[95],"identify":[97],"by":[98],"most":[100],"promising":[101],"ones":[102],"(measured":[103],"terms":[105],"specificity,":[107],"hierarchy,":[108],"importance).":[110],"We":[111],"develop":[112],"test":[114],"collection":[115],"based":[116],"on":[117],"Wikipedia":[118],"demonstrate":[121],"effectiveness":[123],"proposed":[126],"approach.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-08-24T00:00:00"}