{"id":"https://openalex.org/W2083821955","doi":"https://doi.org/10.1145/2644866.2644874","title":"On automatic text segmentation","display_name":"On automatic text segmentation","publication_year":2014,"publication_date":"2014-09-16","ids":{"openalex":"https://openalex.org/W2083821955","doi":"https://doi.org/10.1145/2644866.2644874","mag":"2083821955"},"language":"en","primary_location":{"id":"doi:10.1145/2644866.2644874","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644866.2644874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM symposium on Document engineering","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/A5066992746","display_name":"Boris Dadachev","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Boris Dadachev","raw_affiliation_strings":["Cardiff University, Cardiff, United Kingdom","Cardiff University, Cardiff, UNITED KINGDOM"],"affiliations":[{"raw_affiliation_string":"Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"Cardiff University, Cardiff, UNITED KINGDOM","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091025769","display_name":"Alexander Balinsky","orcid":"https://orcid.org/0000-0002-8151-4462"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexander Balinsky","raw_affiliation_strings":["Cardiff University, Cardiff, United Kingdom","Cardiff University, Cardiff, UNITED KINGDOM"],"affiliations":[{"raw_affiliation_string":"Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"Cardiff University, Cardiff, UNITED KINGDOM","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080473462","display_name":"Helen Balinsky","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156325","display_name":"Hewlett-Packard (United Kingdom)","ror":"https://ror.org/05g4mtv59","country_code":"GB","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210156325"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Helen Balinsky","raw_affiliation_strings":["Hewlett-Packard Laboratories, Bristol, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Laboratories, Bristol, United Kingdom","institution_ids":["https://openalex.org/I4210156325"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066992746"],"corresponding_institution_ids":["https://openalex.org/I79510175"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84994994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.8394520282745361},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8226525783538818},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7730544209480286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.596492350101471},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5270633697509766},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4718461036682129},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.470008909702301},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46652019023895264},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4560333490371704},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4430193305015564},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.43221551179885864},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42118585109710693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40169447660446167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35656481981277466},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.346095472574234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394520282745361},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8226525783538818},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7730544209480286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.596492350101471},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5270633697509766},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4718461036682129},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.470008909702301},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46652019023895264},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4560333490371704},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4430193305015564},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.43221551179885864},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42118585109710693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40169447660446167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35656481981277466},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.346095472574234},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2644866.2644874","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644866.2644874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:86400","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/id/eprint/86400/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1626945812","https://openalex.org/W1710422233","https://openalex.org/W1828401780","https://openalex.org/W1880262756","https://openalex.org/W2027823133","https://openalex.org/W2055098139","https://openalex.org/W2065303853","https://openalex.org/W2098162425","https://openalex.org/W2106918957","https://openalex.org/W2107402508","https://openalex.org/W2112328181","https://openalex.org/W2118229299","https://openalex.org/W2118612506","https://openalex.org/W2148818577","https://openalex.org/W2159083595","https://openalex.org/W2167055684","https://openalex.org/W2997961850","https://openalex.org/W4231510805","https://openalex.org/W4285719527","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W3144569342","https://openalex.org/W2185902295","https://openalex.org/W2003578783","https://openalex.org/W2945274617","https://openalex.org/W2372421320","https://openalex.org/W2057775483","https://openalex.org/W2041871225","https://openalex.org/W2386644571","https://openalex.org/W2387793296","https://openalex.org/W1558398159"],"abstract_inverted_index":{"Automatic":[0],"text":[1,10,36,96,155],"segmentation,":[2],"which":[3],"is":[4,14,101,125],"the":[5,32,147],"task":[6],"of":[7,34,55,112,161,166],"breaking":[8],"a":[9,15,91],"into":[11,43],"topically-consistent":[12],"segments,":[13],"fundamental":[16],"problem":[17],"in":[18,121],"Natural":[19],"Language":[20],"Processing,":[21],"Document":[22],"Classification":[23],"and":[24,46,97,103,115,128,140,150,157],"Information":[25],"Retrieval.":[26],"Text":[27],"segmentation":[28,100,108,132,156],"can":[29,81],"significantly":[30],"improve":[31],"performance":[33],"various":[35],"mining":[37],"algorithms,":[38],"by":[39],"splitting":[40],"heterogeneous":[41],"documents":[42],"homogeneous":[44],"fragments":[45],"thus":[47],"facilitating":[48],"subsequent":[49],"processing.":[50],"Applications":[51],"range":[52],"from":[53,62,69],"screening":[54],"radio":[56],"communication":[57],"transcripts":[58],"to":[59,66,72,130],"document":[60,64,86],"summarization,":[61],"automatic":[63,70,85,95,107,154],"classification":[65],"information":[67],"visualization,":[68],"filtering":[71],"security":[73],"policy":[74],"enforcement":[75],"-":[76],"all":[77],"rely":[78],"on,":[79],"or":[80],"largely":[82],"benefit":[83],"from,":[84],"segmentation.":[87],"In":[88],"this":[89],"article,":[90],"novel":[92],"approach":[93,163],"for":[94,153],"data":[98],"stream":[99],"presented":[102],"studied.":[104],"The":[105],"proposed":[106],"algorithm":[109],"takes":[110],"advantage":[111],"feature":[113],"extraction":[114],"unusual":[116],"behaviour":[117],"detection":[118],"algorithms":[119,152],"developed":[120],"[4,":[122],"5].":[123],"It":[124],"entirely":[126],"unsupervised":[127],"flexible":[129],"allow":[131],"at":[133],"different":[134],"scales,":[135],"such":[136],"as":[137],"short":[138],"paragraphs":[139],"large":[141],"sections.":[142],"We":[143],"also":[144],"briefly":[145],"review":[146],"most":[148],"popular":[149],"important":[151],"present":[158],"detailed":[159],"comparisons":[160],"our":[162],"with":[164],"several":[165],"those":[167],"state-of-the-art":[168],"algorithms.":[169]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}