{"id":"https://openalex.org/W2016801079","doi":"https://doi.org/10.1109/taslp.2015.2405482","title":"Keyword Extraction and Clustering for Document Recommendation in Conversations","display_name":"Keyword Extraction and Clustering for Document Recommendation in Conversations","publication_year":2015,"publication_date":"2015-02-19","ids":{"openalex":"https://openalex.org/W2016801079","doi":"https://doi.org/10.1109/taslp.2015.2405482","mag":"2016801079"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2405482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2405482","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/203854","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086385635","display_name":"Maryam Habibi","orcid":"https://orcid.org/0000-0002-3237-5080"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Maryam Habibi","raw_affiliation_strings":["Idiap, Research Institute and \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), 1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap, Research Institute and \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), 1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044462851","display_name":"Andr\u00e9i Popescu-Belis","orcid":"https://orcid.org/0000-0003-4934-2071"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andrei Popescu-Belis","raw_affiliation_strings":["Idiap, Research Institute and \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), 1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap, Research Institute and \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), 1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.9706,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.99181043,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"23","issue":"4","first_page":"746","last_page":"759"},"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/T10028","display_name":"Topic Modeling","score":0.9909999966621399,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9864000082015991,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8305163383483887},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7895567417144775},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.6947617530822754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6430311799049377},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6267879009246826},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5906235575675964},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5820387005805969},{"id":"https://openalex.org/keywords/submodular-set-function","display_name":"Submodular set function","score":0.5541120767593384},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5534194707870483},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5189261436462402},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4354705810546875},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.42580854892730713},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4239517152309418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3939010500907898},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11571544408798218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305163383483887},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7895567417144775},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.6947617530822754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6430311799049377},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6267879009246826},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5906235575675964},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5820387005805969},{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.5541120767593384},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5534194707870483},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5189261436462402},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4354705810546875},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.42580854892730713},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4239517152309418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3939010500907898},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11571544408798218},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2015.2405482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2405482","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.epfl.ch:203854","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203854","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:203854","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203854","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320321942","display_name":"Hasler Stiftung","ror":"https://ror.org/04m3t9183"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W175385064","https://openalex.org/W1524366219","https://openalex.org/W1525595230","https://openalex.org/W1579690747","https://openalex.org/W1594901598","https://openalex.org/W1600505759","https://openalex.org/W1604286344","https://openalex.org/W1614298861","https://openalex.org/W1680189815","https://openalex.org/W1880262756","https://openalex.org/W1907578970","https://openalex.org/W1977089507","https://openalex.org/W1978394996","https://openalex.org/W1985697096","https://openalex.org/W1995386266","https://openalex.org/W2009388533","https://openalex.org/W2009658355","https://openalex.org/W2021581601","https://openalex.org/W2023188792","https://openalex.org/W2033873263","https://openalex.org/W2045181608","https://openalex.org/W2058089741","https://openalex.org/W2064418625","https://openalex.org/W2073420696","https://openalex.org/W2083613205","https://openalex.org/W2083751884","https://openalex.org/W2094291923","https://openalex.org/W2109297205","https://openalex.org/W2116143388","https://openalex.org/W2125420881","https://openalex.org/W2126689453","https://openalex.org/W2132314908","https://openalex.org/W2134068612","https://openalex.org/W2135043619","https://openalex.org/W2139414852","https://openalex.org/W2141222516","https://openalex.org/W2144933361","https://openalex.org/W2146769536","https://openalex.org/W2147832337","https://openalex.org/W2150924755","https://openalex.org/W2152311362","https://openalex.org/W2153579005","https://openalex.org/W2158018156","https://openalex.org/W2159426623","https://openalex.org/W2163659824","https://openalex.org/W2165599843","https://openalex.org/W2166268996","https://openalex.org/W2166996968","https://openalex.org/W2169150382","https://openalex.org/W2169602691","https://openalex.org/W2170601570","https://openalex.org/W2187898940","https://openalex.org/W2218641061","https://openalex.org/W2296730072","https://openalex.org/W2427789500","https://openalex.org/W3026024608","https://openalex.org/W3118655244","https://openalex.org/W4229917551","https://openalex.org/W4237791300","https://openalex.org/W4294170691","https://openalex.org/W6603931906","https://openalex.org/W6631541997","https://openalex.org/W6636121682","https://openalex.org/W6636510571","https://openalex.org/W6639689704","https://openalex.org/W6680015045","https://openalex.org/W6680753128","https://openalex.org/W6681106510","https://openalex.org/W6681971551","https://openalex.org/W6682691769","https://openalex.org/W6683944584","https://openalex.org/W6684489972","https://openalex.org/W6684679735","https://openalex.org/W6697279800","https://openalex.org/W7015831105"],"related_works":["https://openalex.org/W1595919516","https://openalex.org/W2025763381","https://openalex.org/W3162540683","https://openalex.org/W149061968","https://openalex.org/W2921578339","https://openalex.org/W2617804616","https://openalex.org/W2732846749","https://openalex.org/W2885310545","https://openalex.org/W1492250428","https://openalex.org/W2885586340"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,11,73,77,89,118,123,151,167,185],"problem":[4],"of":[5,13,27,45,76,91,104,109,126,153,177],"keyword":[6,119,145],"extraction":[7],"from":[8,88,143,184],"conversations,":[9],"with":[10,179],"goal":[12],"using":[14,55,161],"these":[15,162],"keywords":[16,87],"to":[17,35,51,70,85,121,137,149,164,181,225],"retrieve,":[18],"for":[19,99,220],"each":[20],"short":[21,40],"conversation":[22,78,182],"fragment,":[23],"a":[24,39,43,96,110,135,217,221],"small":[25],"number":[26],"potentially":[28,49],"relevant":[29,158],"documents,":[30],"which":[31,47,101,114],"can":[32],"be":[33,226],"recommended":[34],"participants.":[36,79],"However,":[37],"even":[38],"fragment":[41],"contains":[42],"variety":[44],"words,":[46],"are":[48,173],"related":[50],"several":[52,194],"topics;":[53],"moreover,":[54],"an":[56,83,92],"automatic":[57],"speech":[58],"recognition":[59],"(ASR)":[60],"system":[61,94,224],"introduces":[62],"errors":[63],"among":[64],"them.":[65],"Therefore,":[66],"it":[67],"is":[68],"difficult":[69],"infer":[71],"precisely":[72],"information":[74],"needs":[75],"We":[80],"first":[81],"propose":[82,134],"algorithm":[84],"extract":[86],"output":[90],"ASR":[93,130],"(or":[95],"manual":[97],"transcript":[98],"testing),":[100],"makes":[102],"use":[103],"topic":[105,213],"modeling":[106],"techniques":[107],"and":[108,128,188,215],"submodular":[111],"reward":[112],"function":[113],"favors":[115],"diversity":[116,125],"in":[117,147,175,228],"set,":[120,146],"match":[122],"potential":[124],"topics":[127],"reduce":[129],"noise.":[131],"Then,":[132],"we":[133],"method":[136],"derive":[138],"multiple":[139],"topically":[140],"separated":[141],"queries":[142,163],"this":[144],"order":[148],"maximize":[150],"chances":[152],"making":[154],"at":[155],"least":[156],"one":[157],"recommendation":[159],"when":[160],"search":[165],"over":[166,204],"English":[168],"Wikipedia.":[169],"The":[170,197],"proposed":[171],"methods":[172,206],"evaluated":[174],"terms":[176],"relevance":[178],"respect":[180],"fragments":[183],"Fisher,":[186],"AMI,":[187],"ELEA":[189],"conversational":[190],"corpora,":[191],"rated":[192],"by":[193],"human":[195],"judges.":[196],"scores":[198],"show":[199],"that":[200,207],"our":[201],"proposal":[202],"improves":[203],"previous":[205],"consider":[208],"only":[209],"word":[210],"frequency":[211],"or":[212],"similarity,":[214],"represents":[216],"promising":[218],"solution":[219],"document":[222],"recommender":[223],"used":[227],"conversations.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}