{"id":"https://openalex.org/W2566297247","doi":"https://doi.org/10.18653/v1/d16-1198","title":"Supervised Keyphrase Extraction as Positive Unlabeled Learning","display_name":"Supervised Keyphrase Extraction as Positive Unlabeled Learning","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2566297247","doi":"https://doi.org/10.18653/v1/d16-1198","mag":"2566297247"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d16-1198","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1198","pdf_url":"https://aclanthology.org/D16-1198.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D16-1198.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055101559","display_name":"Lucas Sterckx","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Lucas Sterckx","raw_affiliation_strings":["Ghent University -iMinds, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University -iMinds, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I39327780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["University of North Texas, Texas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas, Texas, USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075509168","display_name":"Thomas Demeester","orcid":"https://orcid.org/0000-0002-9901-5768"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Thomas Demeester","raw_affiliation_strings":["Ghent University -iMinds, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University -iMinds, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I39327780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084742757","display_name":"Chris Develder","orcid":"https://orcid.org/0000-0003-2707-4176"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Chris Develder","raw_affiliation_strings":["Ghent University -iMinds, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University -iMinds, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I39327780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1924","last_page":"1929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":1.0,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":1.0,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9271000027656555,"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":0.9261999726295471,"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/computer-science","display_name":"Computer science","score":0.6724058389663696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5941240191459656},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.552834153175354},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.46087390184402466},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.43092456459999084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4083186984062195},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.13320401310920715},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09956276416778564},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09134912490844727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6724058389663696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5941240191459656},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.552834153175354},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.46087390184402466},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.43092456459999084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4083186984062195},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.13320401310920715},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09956276416778564},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09134912490844727}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/d16-1198","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1198","pdf_url":"https://aclanthology.org/D16-1198.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:8507315","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8507315","pdf_url":"https://biblio.ugent.be/publication/8507315/file/8507320","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISBN: 978-1-5108-3154-4","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:info:ark/67531/metadc991023","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc991023/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2016 Conference on Empirical Methods in Natural Language Processing, November 1-5, 2016. Austin, TX, United States","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.18653/v1/d16-1198","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1198","pdf_url":"https://aclanthology.org/D16-1198.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322274","display_name":"iMinds","ror":"https://ror.org/03baec336"},{"id":"https://openalex.org/F4320322852","display_name":"Innoviris","ror":"https://ror.org/04af9zr29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2566297247.pdf","grobid_xml":"https://content.openalex.org/works/W2566297247.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W32253530","https://openalex.org/W1490343430","https://openalex.org/W1600284338","https://openalex.org/W1894735736","https://openalex.org/W1907578970","https://openalex.org/W1971947061","https://openalex.org/W2050273484","https://openalex.org/W2064418625","https://openalex.org/W2083214110","https://openalex.org/W2123958887","https://openalex.org/W2129557600","https://openalex.org/W2132442585","https://openalex.org/W2156577800","https://openalex.org/W2160517426","https://openalex.org/W2251470557","https://openalex.org/W2251476947","https://openalex.org/W2295598076","https://openalex.org/W2963113751","https://openalex.org/W3102476541"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W122912556","https://openalex.org/W1586607209","https://openalex.org/W4312414840","https://openalex.org/W2621411691","https://openalex.org/W2271357838","https://openalex.org/W2556866732","https://openalex.org/W2348322200","https://openalex.org/W2981952041","https://openalex.org/W2328989934"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,16,75,97,113,137,146],"noisy":[3,68],"and":[4,27,71,134,152],"unbalanced":[5],"training":[6,53,69],"data":[7,47,70,92],"for":[8,25,55],"supervised":[9,56,78],"keyphrase":[10,17,57,115],"extraction":[11,73],"results":[12],"from":[13,61,149],"the":[14,76,95],"subjectivity":[15],"assignment,":[18],"which":[19],"we":[20],"quantify":[21],"by":[22,93,124],"crowdsourcing":[23],"keyphrases":[24],"news":[26],"fashion":[28],"magazine":[29],"articles":[30,122],"with":[31,90],"many":[32],"annotators":[33,39],"per":[34],"document.":[35],"We":[36,80,109,139],"show":[37,110,153],"that":[38,44,111],"exhibit":[40],"substantial":[41],"disagreement,":[42],"meaning":[43],"single":[45,62],"annotator":[46],"could":[48],"lead":[49,66],"to":[50,67,87,128,143],"very":[51],"different":[52,150],"sets":[54],"extractors.":[58],"Thus,":[59],"annotations":[60],"authors":[63],"or":[64],"readers":[65],"poor":[72],"performance":[74,112],"resulting":[77],"extractor.":[79],"provide":[81],"a":[82,102,118,144],"simple":[83],"but":[84],"effective":[85],"solution":[86],"still":[88],"work":[89],"such":[91],"reweighting":[94],"importance":[96],"unlabeled":[98],"candidate":[99],"phrases":[100],"in":[101],"two":[103],"stage":[104],"Positive":[105],"Unlabeled":[106],"Learning":[107],"setting.":[108],"trained":[114,120],"extractors":[116],"approximates":[117],"classifier":[119],"on":[121],"labeled":[123],"multiple":[125],"annotators,":[126],"leading":[127],"higher":[129],"average":[130],"F":[131],"1":[132],"scores":[133],"better":[135],"rankings":[136],"keyphrases.":[138],"apply":[140],"this":[141],"strategy":[142],"variety":[145],"test":[147],"collections":[148],"backgrounds":[151],"improvements":[154],"over":[155],"strong":[156],"baseline":[157],"models.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}