{"id":"https://openalex.org/W4388860797","doi":"https://doi.org/10.5220/0012179500003598","title":"KRAKEN: A Novel Semantic-Based Approach for Keyphrases Extraction","display_name":"KRAKEN: A Novel Semantic-Based Approach for Keyphrases Extraction","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388860797","doi":"https://doi.org/10.5220/0012179500003598"},"language":"en","primary_location":{"id":"doi:10.5220/0012179500003598","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012179500003598","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0012179500003598","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102781905","display_name":"Simone D\u2019Amico","orcid":"https://orcid.org/0009-0002-2820-0277"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Simone D\u2019Amico","raw_affiliation_strings":["Department of Economics, Management and Statistics, University of Milano-Bicocca, Milan, Italy, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Department of Economics, Management and Statistics, University of Milano-Bicocca, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046882068","display_name":"Lorenzo Malandri","orcid":"https://orcid.org/0000-0002-0222-9365"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Malandri","raw_affiliation_strings":["CRISP Research Centre, University of Milan-Bicocca, Milan, Italy, --- Select a Country ---","Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"CRISP Research Centre, University of Milan-Bicocca, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I66752286"]},{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047827615","display_name":"Fabio Mercorio","orcid":"https://orcid.org/0000-0001-6864-2702"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Mercorio","raw_affiliation_strings":["CRISP Research Centre, University of Milan-Bicocca, Milan, Italy, --- Select a Country ---","Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"CRISP Research Centre, University of Milan-Bicocca, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I66752286"]},{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039716498","display_name":"Mario Mezzanzanica","orcid":"https://orcid.org/0000-0003-0399-2810"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario Mezzanzanica","raw_affiliation_strings":["CRISP Research Centre, University of Milan-Bicocca, Milan, Italy, --- Select a Country ---","Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"CRISP Research Centre, University of Milan-Bicocca, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I66752286"]},{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102781905"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15135807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.7886521816253662},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.545242428779602},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34473228454589844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32816267013549805},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0709078311920166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886521816253662},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.545242428779602},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34473228454589844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32816267013549805},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0709078311920166},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0012179500003598","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012179500003598","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:boa.unimib.it:10281/455025","is_oa":false,"landing_page_url":"https://hdl.handle.net/10281/455025","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0012179500003598","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012179500003598","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"A":[0],"research":[1],"area":[2],"of":[3,25,43,49,79,111,159,165,176],"NLP":[4,52],"is":[5,82,162],"known":[6],"as":[7,101],"keyphrases":[8,56],"extraction,":[9],"which":[10],"aims":[11],"to":[12,54,106,168],"identify":[13],"words":[14,139,179],"and":[15,64,96,123,150,183],"expressions":[16],"in":[17,60,73,140],"a":[18,34,58,84,108,125,166],"text":[19,27,59,93],"that":[20,114,128],"comprehensively":[21],"represent":[22],"the":[23,26,67,74,112,136,141,163,170,174,178,181,185,189],"content":[24],"itself.":[28],"In":[29],"this":[30,80,160],"study,":[31],"we":[32,65,121,146],"introduce":[33],"new":[35,126],"approach":[36,86,153],"called":[37],"KRAKEN":[38],"(Keyphrease":[39],"extRAction":[40],"maKing":[41],"use":[42],"EmbeddiNgs).":[44],"Our":[45],"method":[46,127],"takes":[47],"advantage":[48],"widely":[50],"used":[51,105],"techniques":[53,95],"extract":[55],"from":[57,188],"an":[61],"unsupervised":[62],"manner":[63],"compare":[66,151],"results":[68],"with":[69,154],"well-known":[70],"benchmark":[71,148],"datasets":[72,149],"literature.":[75],"The":[76],"main":[77],"contribution":[78,158],"work":[81,161],"developing":[83],"novel":[85],"for":[87,132],"keyphrase":[88],"extraction.":[89],"Both":[90],"natural":[91],"language":[92],"preprocessing":[94],"distributional":[97],"semantics":[98],"techniques,":[99],"such":[100],"word":[102,130],"embeddings,":[103],"are":[104],"obtain":[107],"vector":[109],"representation":[110],"texts":[113],"maintains":[115],"their":[116],"semantic":[117],"meaning.":[118],"Through":[119],"KRAKEN,":[120,145],"propose":[122],"design":[124],"exploits":[129],"embedding":[131],"identifying":[133],"keyphrases,":[134,172],"considering":[135,173],"relationship":[137],"among":[138],"text.":[142,191],"To":[143],"evaluate":[144],"employ":[147],"our":[152],"state-of-the-art":[155],"methods.":[156],"Another":[157],"introduction":[164],"metric":[167],"rank":[169],"identified":[171],"relatedness":[175],"both":[177],"within":[180],"phrases":[182,187],"all":[184],"extracted":[186],"same":[190]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2023-11-22T00:00:00"}