{"id":"https://openalex.org/W4406458378","doi":"https://doi.org/10.1109/bigdata62323.2024.10824946","title":"LongKey: Keyphrase Extraction for Long Documents","display_name":"LongKey: Keyphrase Extraction for Long Documents","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458378","doi":"https://doi.org/10.1109/bigdata62323.2024.10824946"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10824946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10824946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-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/A5114472877","display_name":"Jeovane Honorio Alves","orcid":null},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":true,"raw_author_name":"Jeovane Honorio Alves","raw_affiliation_strings":["University of Luxembourg,SEDAN-SnT"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg,SEDAN-SnT","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069228908","display_name":"Radu State","orcid":"https://orcid.org/0000-0002-4751-9577"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Radu State","raw_affiliation_strings":["University of Luxembourg,SEDAN-SnT"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg,SEDAN-SnT","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025126119","display_name":"Cinthia Obladen de Almendra Freitas\u200d","orcid":"https://orcid.org/0000-0002-7015-094X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cinthia Obladen de Almendra Freitas","raw_affiliation_strings":["Pontifícia Universidade Católica do Paraná,Graduate Program in Law (PPGD)"],"affiliations":[{"raw_affiliation_string":"Pontifícia Universidade Católica do Paraná,Graduate Program in Law (PPGD)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071288743","display_name":"Jean Paul Barddal","orcid":"https://orcid.org/0000-0001-9928-854X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean Paul Barddal","raw_affiliation_strings":["Pontifícia Universidade Católica do Paraná,Graduate Program in Informatics (PPGIa)"],"affiliations":[{"raw_affiliation_string":"Pontifícia Universidade Católica do Paraná,Graduate Program in Informatics (PPGIa)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114472877"],"corresponding_institution_ids":["https://openalex.org/I186903577"],"apc_list":null,"apc_paid":null,"fwci":1.0473,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82425845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1706","last_page":"1715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T13317","display_name":"Media, Communication, and Education","score":0.9345999956130981,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7219496369361877},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5612988471984863},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5114787817001343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4412391483783722},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38418087363243103},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.052939027547836304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219496369361877},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5612988471984863},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5114787817001343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4412391483783722},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38418087363243103},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.052939027547836304},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10824946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10824946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1034019924","https://openalex.org/W1490343430","https://openalex.org/W1492471138","https://openalex.org/W1528825546","https://openalex.org/W2103479483","https://openalex.org/W2133286915","https://openalex.org/W2143017621","https://openalex.org/W2750779823","https://openalex.org/W2890484448","https://openalex.org/W2896457183","https://openalex.org/W2963265326","https://openalex.org/W2970467549","https://openalex.org/W3005871041","https://openalex.org/W3015468748","https://openalex.org/W3034379969","https://openalex.org/W3208384853","https://openalex.org/W4205807230","https://openalex.org/W4221153042","https://openalex.org/W4248875918","https://openalex.org/W4308045040","https://openalex.org/W4376988925","https://openalex.org/W4382246105","https://openalex.org/W4385570859","https://openalex.org/W4386566579","https://openalex.org/W4392942700","https://openalex.org/W6631501603","https://openalex.org/W6631793906","https://openalex.org/W6675317306","https://openalex.org/W6679051890","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6776048684","https://openalex.org/W6810633241","https://openalex.org/W6811300139"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,52],"an":[1,69,119],"era":[2],"of":[3,13],"information":[4],"overload,":[5],"manually":[6],"annotating":[7],"the":[8,90],"vast":[9],"and":[10,15,94,104,115,128],"growing":[11],"corpus":[12],"documents":[14,40],"scholarly":[16],"papers":[17],"is":[18],"increasingly":[19],"impractical.":[20],"Automated":[21],"keyphrase":[22,85,107,122],"extraction":[23,108,123],"addresses":[24],"this":[25,53],"challenge":[26],"by":[27],"identifying":[28],"representative":[29],"terms":[30],"within":[31],"texts.":[32],"However,":[33],"most":[34],"existing":[35,102],"methods":[36],"focus":[37],"on":[38,89],"short":[39],"(up":[41],"to":[42,73,83],"512":[43],"tokens),":[44],"leaving":[45],"a":[46,58,80],"gap":[47],"in":[48,121],"processing":[49],"long-context":[50],"documents.":[51],"paper,":[54],"we":[55],"introduce":[56],"LongKey,":[57],"novel":[59],"framework":[60],"for":[61,124],"extracting":[62],"keyphrases":[63],"from":[64],"lengthy":[65],"documents,":[66],"which":[67],"uses":[68,79],"encoder-based":[70],"language":[71,105],"model":[72],"capture":[74],"extended":[75],"text":[76,126],"intricacies.":[77],"LongKey":[78,99],"max-pooling":[81],"embedder":[82],"enhance":[84],"candidate":[86],"representation.":[87],"Validated":[88],"comprehensive":[91],"LDKP":[92],"datasets":[93],"six":[95],"diverse,":[96],"unseen":[97],"datasets,":[98],"consistently":[100],"outperforms":[101],"unsupervised":[103],"model-based":[106],"methods.":[109],"Our":[110],"findings":[111],"demonstrate":[112],"LongKey\u2019s":[113],"versatility":[114],"superior":[116],"performance,":[117],"marking":[118],"advancement":[120],"varied":[125],"lengths":[127],"domains.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}