{"id":"https://openalex.org/W190156351","doi":"https://doi.org/10.21437/interspeech.2009-119","title":"Multiple text segmentation for statistical language modeling","display_name":"Multiple text segmentation for statistical language modeling","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W190156351","doi":"https://doi.org/10.21437/interspeech.2009-119","mag":"190156351"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-119","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01393605","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039006703","display_name":"Sopheap Seng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sopheap Seng","raw_affiliation_strings":["Communication Langagi\u00e8re et Interaction Personne-Syst\u00e8me"],"affiliations":[{"raw_affiliation_string":"Communication Langagi\u00e8re et Interaction Personne-Syst\u00e8me","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108120865","display_name":"Laurent Besacier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent Besacier","raw_affiliation_strings":["Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole"],"affiliations":[{"raw_affiliation_string":"Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041939827","display_name":"Brigitte Bigi","orcid":"https://orcid.org/0000-0003-1834-6918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brigitte Bigi","raw_affiliation_strings":["Communication Langagi\u00e8re et Interaction Personne-Syst\u00e8me"],"affiliations":[{"raw_affiliation_string":"Communication Langagi\u00e8re et Interaction Personne-Syst\u00e8me","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038215006","display_name":"Eric Castelli","orcid":"https://orcid.org/0000-0003-2978-2619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Castelli","raw_affiliation_strings":["International Research Institute MICA"],"affiliations":[{"raw_affiliation_string":"International Research Institute MICA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039006703"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4505,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70979001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2663","last_page":"2666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing 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/T10181","display_name":"Natural Language Processing 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9975000023841858,"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":0.8597773909568787},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7597203254699707},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.722305953502655},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7175220847129822},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.6548479795455933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6450096368789673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6380714178085327},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.6110205054283142},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5171636939048767},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5162805914878845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.499969482421875},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43819698691368103},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4190746247768402},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14554071426391602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597773909568787},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7597203254699707},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.722305953502655},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7175220847129822},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6548479795455933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6450096368789673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6380714178085327},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.6110205054283142},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5171636939048767},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5162805914878845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.499969482421875},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43819698691368103},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4190746247768402},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14554071426391602},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-119","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01393605v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01393605","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"http://www.isca-speech.org/archive/interspeech_2009/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01393605v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01393605","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"http://www.isca-speech.org/archive/interspeech_2009/","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W14331692","https://openalex.org/W92696887","https://openalex.org/W1212668227","https://openalex.org/W1654022110","https://openalex.org/W2032942114","https://openalex.org/W2097341304"],"related_works":["https://openalex.org/W2589064161","https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W155946694","https://openalex.org/W1555968995","https://openalex.org/W4307474317","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2057384730"],"abstract_inverted_index":{"International":[0],"audience":[1]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
