{"id":"https://openalex.org/W3207617013","doi":"https://doi.org/10.1145/3468268","title":"BATS: A Spectral Biclustering Approach to Single Document Topic Modeling and Segmentation","display_name":"BATS: A Spectral Biclustering Approach to Single Document Topic Modeling and Segmentation","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3207617013","doi":"https://doi.org/10.1145/3468268","mag":"3207617013"},"language":"en","primary_location":{"id":"doi:10.1145/3468268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468268","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-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/A5014988656","display_name":"Qiong Wu","orcid":"https://orcid.org/0000-0001-7724-8221"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiong Wu","raw_affiliation_strings":["Department of Computer Science, College of William and Mary, Williamsburg, Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of William and Mary, Williamsburg, Virginia","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011020460","display_name":"Adam Hare","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Hare","raw_affiliation_strings":["Zoomi Inc., Blue Bell, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zoomi Inc., Blue Bell, Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631506","display_name":"Sirui Wang","orcid":"https://orcid.org/0000-0001-9519-5741"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sirui Wang","raw_affiliation_strings":["Department of Computer Science, College of William and Mary, Williamsburg, Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of William and Mary, Williamsburg, Virginia","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045947650","display_name":"Yuwei Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuwei Tu","raw_affiliation_strings":["Zoomi Inc., Blue Bell, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zoomi Inc., Blue Bell, Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101738056","display_name":"Zhenming Liu","orcid":"https://orcid.org/0000-0001-9494-8748"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenming Liu","raw_affiliation_strings":["Department of Computer Science, College of William and Mary, Williamsburg, Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of William and Mary, Williamsburg, Virginia","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020399355","display_name":"Christopher G. Brinton","orcid":"https://orcid.org/0000-0003-2771-3521"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher G. Brinton","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100630059","display_name":"Yanhua Li","orcid":"https://orcid.org/0000-0001-8972-503X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanhua Li","raw_affiliation_strings":["Department of Computer Science, Worchester Polytechnic Institute, Worcester, Massachusetts"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Worchester Polytechnic Institute, Worcester, Massachusetts","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2999,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8405268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"12","issue":"5","first_page":"1","last_page":"29"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9937999844551086,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8996479511260986},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.701698899269104},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6224736571311951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5710848569869995},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5552590489387512},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4516330659389496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4268473982810974},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.42590951919555664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3819185495376587},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3352239727973938},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3345797061920166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8996479511260986},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.701698899269104},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6224736571311951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710848569869995},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5552590489387512},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4516330659389496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4268473982810974},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42590951919555664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3819185495376587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3352239727973938},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3345797061920166},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3468268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468268","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314598","display_name":"Charles Koch Foundation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1557074680","https://openalex.org/W1614298861","https://openalex.org/W1714665356","https://openalex.org/W1880262756","https://openalex.org/W1973207991","https://openalex.org/W1979469248","https://openalex.org/W1981081578","https://openalex.org/W1994448786","https://openalex.org/W2024364296","https://openalex.org/W2038043464","https://openalex.org/W2061922307","https://openalex.org/W2063904635","https://openalex.org/W2066873261","https://openalex.org/W2080179128","https://openalex.org/W2089923519","https://openalex.org/W2107743791","https://openalex.org/W2110485445","https://openalex.org/W2119998616","https://openalex.org/W2130158951","https://openalex.org/W2132914434","https://openalex.org/W2133576408","https://openalex.org/W2147152072","https://openalex.org/W2150593711","https://openalex.org/W2150731624","https://openalex.org/W2159083595","https://openalex.org/W2166753626","https://openalex.org/W2168332560","https://openalex.org/W2171313960","https://openalex.org/W2178725228","https://openalex.org/W2208334037","https://openalex.org/W2250539671","https://openalex.org/W2321470647","https://openalex.org/W2416799949","https://openalex.org/W2434205482","https://openalex.org/W2461271816","https://openalex.org/W2472333518","https://openalex.org/W2561715741","https://openalex.org/W2744808284","https://openalex.org/W2749627623","https://openalex.org/W2750686086","https://openalex.org/W2750779823","https://openalex.org/W2750981579","https://openalex.org/W2782822144","https://openalex.org/W2788615138","https://openalex.org/W2896457183","https://openalex.org/W2896763200","https://openalex.org/W2926555354","https://openalex.org/W2946516957","https://openalex.org/W2962716111","https://openalex.org/W2962878234","https://openalex.org/W2962943175","https://openalex.org/W2963563735","https://openalex.org/W2963726741","https://openalex.org/W2970507669","https://openalex.org/W2973182536","https://openalex.org/W3020633614","https://openalex.org/W3047595056","https://openalex.org/W3101767658","https://openalex.org/W3101919829","https://openalex.org/W3200421407","https://openalex.org/W4241792331","https://openalex.org/W4288253152"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2275524962","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775"],"abstract_inverted_index":{"Existing":[0],"topic":[1,79,203,205],"modeling":[2,126],"and":[3,35,103,127,139,168,170,181,208],"text":[4,21,48],"segmentation":[5],"methodologies":[6],"generally":[7],"require":[8],"large":[9],"datasets":[10,192],"for":[11,38],"training,":[12],"limiting":[13],"their":[14],"capabilities":[15],"when":[16,42,201],"only":[17,72,101],"small":[18],"collections":[19],"of":[20,32,49,93,166,174],"are":[22],"available.":[23],"In":[24,51],"this":[25],"work,":[26],"we":[27,59,75,114],"reexamine":[28],"the":[29],"inter-related":[30],"problems":[31],"\u201ctopic":[33],"identification\u201d":[34],"\u201ctext":[36],"segmentation\u201d":[37],"sparse":[39,66],"document":[40,98],"learning,":[41],"there":[43],"is":[44,65,86],"a":[45,53,90,143,156,172],"single":[46,57,97],"new":[47,144],"interest.":[50],"developing":[52],"methodology":[54,120],"to":[55,71,124,135,151,185],"handle":[56],"documents,":[58],"face":[60],"two":[61],"major":[62],"challenges.":[63],"First":[64],"information":[67,150],":":[68,89],"with":[69],"access":[70],"one":[73],"document,":[74],"cannot":[76],"train":[77],"traditional":[78],"models":[80],"or":[81,108],"deep":[82],"learning":[83],"algorithms.":[84],"Second":[85],"significant":[87],"noise":[88,102,179],"considerable":[91],"portion":[92],"words":[94,167,180,184],"in":[95],"any":[96],"will":[99],"produce":[100],"not":[104],"help":[105],"discern":[106],"topics":[107,138],"segments.":[109],"To":[110],"tackle":[111],"these":[112],"issues,":[113],"design":[115],"an":[116],"unsupervised,":[117],"computationally":[118],"efficient":[119],"called":[121],"Biclustering":[122],"Approach":[123],"Topic":[125],"Segmentation":[128],"(BATS).":[129],"BATS":[130],"leverages":[131],"three":[132],"key":[133],"ideas":[134],"simultaneously":[136],"identify":[137],"segment":[140],"text:":[141],"(i)":[142],"mechanism":[145],"that":[146,162,177,194],"uses":[147],"word":[148],"order":[149],"reduce":[152],"sample":[153],"complexity,":[154],"(ii)":[155],"statistically":[157],"sound":[158],"graph-based":[159],"biclustering":[160],"technique":[161],"identifies":[163],"latent":[164],"structures":[165],"sentences,":[169],"(iii)":[171],"collection":[173],"effective":[175],"heuristics":[176],"remove":[178],"award":[182],"important":[183],"further":[186],"improve":[187],"performance.":[188],"Experiments":[189],"on":[190],"six":[191],"show":[193],"our":[195],"approach":[196],"outperforms":[197],"several":[198],"state-of-the-art":[199],"baselines":[200],"considering":[202],"coherence,":[204],"diversity,":[206],"segmentation,":[207],"runtime":[209],"comparison":[210],"metrics.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}