{"id":"https://openalex.org/W2252111831","doi":"https://doi.org/10.18653/v1/d13-1130","title":"Leveraging Lexical Cohesion and Disruption for Topic Segmentation","display_name":"Leveraging Lexical Cohesion and Disruption for Topic Segmentation","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2252111831","doi":"https://doi.org/10.18653/v1/d13-1130","mag":"2252111831"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d13-1130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1130","pdf_url":"https://aclanthology.org/D13-1130.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D13-1130.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043955945","display_name":"Anca-Roxana \u015eimon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anca-Roxana \u015eimon","raw_affiliation_strings":["TEXMEX - Multimedia content-based indexing (Campus de Beaulieu, 35042 Rennes cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEXMEX - Multimedia content-based indexing (Campus de Beaulieu, 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008190208","display_name":"Guillaume Gravier","orcid":"https://orcid.org/0000-0002-2266-5682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Gravier","raw_affiliation_strings":["TEXMEX - Multimedia content-based indexing (Campus de Beaulieu, 35042 Rennes cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEXMEX - Multimedia content-based indexing (Campus de Beaulieu, 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005508604","display_name":"Pascale S\u00e9billot","orcid":"https://orcid.org/0000-0002-5429-4302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pascale S\u00e9billot","raw_affiliation_strings":["TEXMEX - Multimedia content-based indexing (Campus de Beaulieu, 35042 Rennes cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEXMEX - Multimedia content-based indexing (Campus de Beaulieu, 35042 Rennes cedex - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1314","last_page":"1324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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/segmentation","display_name":"Segmentation","score":0.7841402292251587},{"id":"https://openalex.org/keywords/cohesion","display_name":"Cohesion (chemistry)","score":0.7732603549957275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770013153553009},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6900966763496399},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6428328156471252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5622218251228333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5137225389480591},{"id":"https://openalex.org/keywords/classification-of-discontinuities","display_name":"Classification of discontinuities","score":0.42917516827583313},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4266262352466583},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.4127039909362793},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29143422842025757},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12409964203834534},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12186667323112488},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.12164413928985596}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7841402292251587},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.7732603549957275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770013153553009},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6900966763496399},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6428328156471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5622218251228333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5137225389480591},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.42917516827583313},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4266262352466583},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.4127039909362793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29143422842025757},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12409964203834534},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12186667323112488},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.12164413928985596},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d13-1130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1130","pdf_url":"https://aclanthology.org/D13-1130.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00867011v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00867011","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":"International Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, Oct 2013, Seattle, United States. pp.1314--1324","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/d13-1130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1130","pdf_url":"https://aclanthology.org/D13-1130.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252111831.pdf","grobid_xml":"https://content.openalex.org/works/W2252111831.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1572970401","https://openalex.org/W1582534817","https://openalex.org/W1626945812","https://openalex.org/W1828401780","https://openalex.org/W2016243284","https://openalex.org/W2017244362","https://openalex.org/W2027823133","https://openalex.org/W2028757787","https://openalex.org/W2050833605","https://openalex.org/W2074276536","https://openalex.org/W2083393647","https://openalex.org/W2098337925","https://openalex.org/W2100626830","https://openalex.org/W2107402508","https://openalex.org/W2112910976","https://openalex.org/W2118612506","https://openalex.org/W2124741472","https://openalex.org/W2133793355","https://openalex.org/W2139042198","https://openalex.org/W2148818577","https://openalex.org/W2159083595","https://openalex.org/W2167702024","https://openalex.org/W2408338990","https://openalex.org/W2414109411","https://openalex.org/W3161085400"],"related_works":["https://openalex.org/W3142119062","https://openalex.org/W2740662036","https://openalex.org/W159209093","https://openalex.org/W589103562","https://openalex.org/W1991220724","https://openalex.org/W2251234095","https://openalex.org/W131522978","https://openalex.org/W2250768577","https://openalex.org/W2160717663","https://openalex.org/W2798990287"],"abstract_inverted_index":{"Topic":[0],"segmentation":[1,24],"classically":[2],"relies":[3],"on":[4,56,62,110],"one":[5],"of":[6,42,67,76,87],"two":[7],"criteria,":[8],"either":[9,88],"finding":[10],"areas":[11],"with":[12,85,113],"coherent":[13],"vocabulary":[14,118],"use":[15],"or":[16,90,95],"detecting":[17],"discontinuities.In":[18],"this":[19],"paper,":[20],"we":[21],"propose":[22],"a":[23,33,63,78],"criterion":[25,44],"combining":[26],"both":[27],"lexical":[28],"cohesion":[29],"and":[30,45,61,93,116],"disruption,":[31],"enabling":[32],"trade-off":[34],"between":[35],"the":[36,39,43,74,105],"two.We":[37],"provide":[38],"mathematical":[40],"formulation":[41],"an":[46],"efficient":[47],"graph":[48],"based":[49],"decoding":[50],"algorithm":[51,106],"for":[52],"topic":[53,97],"segmentation.Experimental":[54],"results":[55],"standard":[57],"textual":[58],"data":[59],"sets":[60],"more":[64,101],"challenging":[65],"corpus":[66],"automatically":[68],"transcribed":[69],"broadcast":[70],"news":[71],"shows":[72],"demonstrate":[73],"benefit":[75,100],"such":[77],"combination.Gains":[79],"were":[80],"observed":[81],"in":[82],"all":[83],"conditions,":[84],"segments":[86,99,115],"regular":[89],"varying":[91],"length":[92],"abrupt":[94],"smooth":[96],"shifts.Long":[98],"than":[102],"short":[103,114],"segments.However":[104],"has":[107],"proven":[108],"robust":[109],"automatic":[111],"transcripts":[112],"limited":[117],"reoccurrences.":[119]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}