{"id":"https://openalex.org/W2291368429","doi":"https://doi.org/10.21437/interspeech.2015-45","title":"Study of entity-topic models for OOV proper name retrieval","display_name":"Study of entity-topic models for OOV proper name retrieval","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2291368429","doi":"https://doi.org/10.21437/interspeech.2015-45","mag":"2291368429"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-45","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5023803850","display_name":"Imran Sheikh","orcid":"https://orcid.org/0000-0001-5041-7398"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Imran Sheikh","raw_affiliation_strings":["PAROLE - Analysis, perception and recognition of speech (France)","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAROLE - Analysis, perception and recognition of speech (France)","institution_ids":[]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073463405","display_name":"Irina Illina","orcid":"https://orcid.org/0000-0003-2598-4643"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Irina Illina","raw_affiliation_strings":["PAROLE - Analysis, perception and recognition of speech (France)","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAROLE - Analysis, perception and recognition of speech (France)","institution_ids":[]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046546502","display_name":"Dominique Fohr","orcid":null},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Fohr","raw_affiliation_strings":["PAROLE - Analysis, perception and recognition of speech (France)","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAROLE - Analysis, perception and recognition of speech (France)","institution_ids":[]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)","institution_ids":["https://openalex.org/I90183372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2259,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90906683,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1344","last_page":"1348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9976999759674072,"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":0.8242151737213135},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6489442586898804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6255881786346436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6168314814567566},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5969621539115906},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5756686329841614},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5722797513008118},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5652921795845032},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4928421974182129},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46976280212402344},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4369817078113556},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4180348515510559},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4131363034248352},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0891154408454895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242151737213135},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6489442586898804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6255881786346436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6168314814567566},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5969621539115906},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5756686329841614},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5722797513008118},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5652921795845032},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4928421974182129},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46976280212402344},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4369817078113556},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4180348515510559},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4131363034248352},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0891154408454895},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-45","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W103603550","https://openalex.org/W119112377","https://openalex.org/W151556337","https://openalex.org/W1524340867","https://openalex.org/W1532325895","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1984251878","https://openalex.org/W2007119365","https://openalex.org/W2035573568","https://openalex.org/W2042980227","https://openalex.org/W2076762622","https://openalex.org/W2100068632","https://openalex.org/W2138649166","https://openalex.org/W2146688305","https://openalex.org/W2147152072","https://openalex.org/W2147463029","https://openalex.org/W2169401934","https://openalex.org/W2226562530","https://openalex.org/W2403088945","https://openalex.org/W2964076070"],"related_works":["https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4389543811"],"abstract_inverted_index":{"Retrieving":[0],"Proper":[1],"Names":[2],"(PNs)":[3,87],"relevant":[4,29],"to":[5,24,81],"an":[6,134],"audio":[7,31],"document\r\ncan":[8],"improve":[9],"speech":[10],"recognition":[11],"and":[12,88,97,107],"content":[13],"based":[14],"audio-video\r\nindexing.":[15],"Latent":[16],"Dirichlet":[17],"Allocation":[18],"(LDA)":[19],"topic":[20],"model":[21],"has\r\nbeen":[22],"used":[23],"retrieve":[25],"Out-Of-Vocabulary":[26],"(OOV)":[27],"PNs":[28,40],"to\r\nan":[30],"document":[32],"with":[33,94],"good":[34],"recall":[35],"rates.":[36],"However,":[37],"retrieval":[38,93],"of\r\nOOV":[39],"using":[41],"LDA":[42,80,124],"is":[43],"affected":[44,102],"by":[45,103],"two":[46],"issues,":[47],"which":[48],"we":[49],"study\r\nin":[50],"this":[51],"paper:":[52],"(1)Word":[53],"Frequency":[54],"Bias":[55],"(less":[56],"frequent":[57],"OOV":[58,117],"PNs\r\nare":[59],"ranked":[60],"lower);":[61],"(2)":[62],"Loss":[63],"of":[64,79,109],"Specificity":[65],"(the":[66],"reduced":[67],"topic\r\nspace":[68],"representation":[69],"loses":[70],"lexical":[71,120],"context).":[72],"Entity-Topic":[73,95],"models\r\nhave":[74],"been":[75],"proposed":[76,113],"as":[77,125,127],"extensions":[78],"specifically":[82],"learn\r\nrelations":[83],"between":[84],"words,":[85],"entities":[86],"topics.":[89],"We":[90],"study\r\nOOV":[91],"PN":[92,118],"models":[96],"show":[98,133],"that":[99],"they\r\nare":[100],"also":[101],"word":[104],"frequency":[105],"bias":[106],"loss":[108],"specificity.\r\nWe":[110],"evaluate":[111],"our":[112],"methods":[114],"for":[115,123,128],"rare":[116],"re-ranking\r\nand":[119],"context":[121],"re-ranking":[122],"well":[126],"Entity-\r\nTopic":[129],"models.":[130],"The":[131],"results":[132],"improvement":[135],"in":[136],"both":[137],"Recall\r\nand":[138],"the":[139],"Mean":[140],"Average":[141],"Precision.":[142]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}