{"id":"https://openalex.org/W2067002391","doi":"https://doi.org/10.1145/2484028.2484062","title":"An unsupervised topic segmentation model incorporating word order","display_name":"An unsupervised topic segmentation model incorporating word order","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2067002391","doi":"https://doi.org/10.1145/2484028.2484062","mag":"2067002391"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2484028.2484062","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2484028.2484062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2484028.2484062","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082611298","display_name":"Shoaib Jameel","orcid":"https://orcid.org/0000-0001-7534-3313"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shoaib Jameel","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018582154","display_name":"Wai Lam","orcid":"https://orcid.org/0000-0001-5479-377X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082611298"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":20.1977,"has_fulltext":true,"cited_by_count":58,"citation_normalized_percentile":{"value":0.99352021,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9987000226974487,"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":0.8109429478645325},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.648269772529602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.62452632188797},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5913686156272888},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5628190636634827},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5484111309051514},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.521372377872467},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.44530999660491943},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4397708475589752},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.4306170642375946},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3829348087310791},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08423495292663574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109429478645325},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.648269772529602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.62452632188797},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5913686156272888},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5628190636634827},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5484111309051514},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.521372377872467},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44530999660491943},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4397708475589752},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.4306170642375946},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3829348087310791},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08423495292663574},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2484028.2484062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2484028.2484062","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2484028.2484062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2484028.2484062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2484028.2484062","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2484028.2484062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2067002391.pdf","grobid_xml":"https://content.openalex.org/works/W2067002391.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W8812172","https://openalex.org/W106244805","https://openalex.org/W114923250","https://openalex.org/W1498269992","https://openalex.org/W1557074680","https://openalex.org/W1614151208","https://openalex.org/W1781198478","https://openalex.org/W1828401780","https://openalex.org/W1862888253","https://openalex.org/W1878153963","https://openalex.org/W1880262756","https://openalex.org/W1984251878","https://openalex.org/W1989270275","https://openalex.org/W2001082470","https://openalex.org/W2015706532","https://openalex.org/W2021378816","https://openalex.org/W2027823133","https://openalex.org/W2033265738","https://openalex.org/W2046677795","https://openalex.org/W2053569739","https://openalex.org/W2055337076","https://openalex.org/W2070740689","https://openalex.org/W2084015864","https://openalex.org/W2100626830","https://openalex.org/W2102705050","https://openalex.org/W2104210067","https://openalex.org/W2106490775","https://openalex.org/W2109450366","https://openalex.org/W2112050062","https://openalex.org/W2126200466","https://openalex.org/W2129317206","https://openalex.org/W2134731454","https://openalex.org/W2140920152","https://openalex.org/W2142522063","https://openalex.org/W2142841267","https://openalex.org/W2152960946","https://openalex.org/W2157574662","https://openalex.org/W2158266063","https://openalex.org/W2159083595","https://openalex.org/W2163738067","https://openalex.org/W2169606435","https://openalex.org/W2170658740"],"related_works":["https://openalex.org/W2160402959","https://openalex.org/W2352674739","https://openalex.org/W2783657965","https://openalex.org/W2393940967","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2159591557","https://openalex.org/W2115592387","https://openalex.org/W2905950556"],"abstract_inverted_index":{"We":[0,73,84],"present":[1],"a":[2,9,47,128],"new":[3],"unsupervised":[4],"topic":[5,22],"discovery":[6],"model":[7,25,99],"for":[8],"collection":[10],"of":[11,19,54,56,103],"text":[12,105],"documents.":[13],"In":[14,37,63],"contrast":[15],"to":[16,112,126],"the":[17,20,29,44,101,110,121,124],"majority":[18],"state-of-the-art":[21],"models,":[23],"our":[24,98],"does":[26],"not":[27],"break":[28],"document's":[30],"structure":[31],"such":[32,108],"as":[33,109],"paragraphs":[34],"and":[35,61,95,136],"sentences.":[36],"addition,":[38,64],"it":[39,49,65],"preserves":[40],"word":[41],"order":[42],"in":[43,70,120],"document.":[45],"As":[46],"result,":[48],"can":[50,66],"generate":[51,67],"two":[52],"levels":[53],"topics":[55,116],"different":[57,93],"granularity,":[58],"namely,":[59],"segment-topics":[60],"word-topics.":[62],"n-gram":[68,118],"words":[69,119],"each":[71],"topic.":[72],"also":[74],"develop":[75],"an":[76],"approximate":[77],"inference":[78],"scheme":[79],"using":[80,88],"Gibbs":[81],"sampling":[82],"method.":[83],"conduct":[85],"extensive":[86],"experiments":[87],"publicly":[89],"available":[90],"data":[91],"from":[92],"collections":[94],"show":[96],"that":[97],"improves":[100],"quality":[102],"several":[104],"mining":[106],"tasks":[107],"ability":[111,125],"support":[113],"fine":[114],"grained":[115],"with":[117],"correlation":[122],"graph,":[123],"segment":[127],"document":[129,134,137],"into":[130],"topically":[131],"coherent":[132],"sections,":[133],"classification,":[135],"likelihood":[138],"estimation.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":33},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}