{"id":"https://openalex.org/W2111344417","doi":"https://doi.org/10.1145/2396761.2396862","title":"Two-part segmentation of text documents","display_name":"Two-part segmentation of text documents","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2111344417","doi":"https://doi.org/10.1145/2396761.2396862","mag":"2111344417"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2396862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2396862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","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/A5113740386","display_name":"P Deepak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Deepak P.","raw_affiliation_strings":["IBM Research - India, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM Research - India, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045869355","display_name":"Karthik Visweswariah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Karthik Visweswariah","raw_affiliation_strings":["IBM Research - India, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM Research - India, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035835846","display_name":"Nirmalie Wiratunga","orcid":"https://orcid.org/0000-0003-4040-2496"},"institutions":[{"id":"https://openalex.org/I522815984","display_name":"Robert Gordon University","ror":"https://ror.org/04f0qj703","country_code":"GB","type":"education","lineage":["https://openalex.org/I522815984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nirmalie Wiratunga","raw_affiliation_strings":["Robert Gordon University, Aberdeen, United Kingdom","Robert Gordon University, Aberdeen. United Kingdom"],"affiliations":[{"raw_affiliation_string":"Robert Gordon University, Aberdeen, United Kingdom","institution_ids":["https://openalex.org/I522815984"]},{"raw_affiliation_string":"Robert Gordon University, Aberdeen. United Kingdom","institution_ids":["https://openalex.org/I522815984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090767222","display_name":"Sadiq Sani","orcid":"https://orcid.org/0000-0001-9784-8398"},"institutions":[{"id":"https://openalex.org/I522815984","display_name":"Robert Gordon University","ror":"https://ror.org/04f0qj703","country_code":"GB","type":"education","lineage":["https://openalex.org/I522815984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sadiq Sani","raw_affiliation_strings":["Robert Gordon University, Aberdeen, United Kingdom","Robert Gordon University, Aberdeen. United Kingdom"],"affiliations":[{"raw_affiliation_string":"Robert Gordon University, Aberdeen, United Kingdom","institution_ids":["https://openalex.org/I522815984"]},{"raw_affiliation_string":"Robert Gordon University, Aberdeen. United Kingdom","institution_ids":["https://openalex.org/I522815984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113740386"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":1.2844,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83846364,"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":"793","last_page":"802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9976999759674072,"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":0.8066456317901611},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7235012054443359},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.6682947278022766},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.6287903785705566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5946471095085144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5852094888687134},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5039722323417664},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.46275991201400757},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46220776438713074},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4162070155143738},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39081114530563354},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.09634649753570557},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08656701445579529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066456317901611},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7235012054443359},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6682947278022766},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.6287903785705566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946471095085144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5852094888687134},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5039722323417664},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.46275991201400757},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46220776438713074},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4162070155143738},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39081114530563354},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.09634649753570557},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08656701445579529},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2396761.2396862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2396862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:openair.rgu.ac.uk:10059/1830","is_oa":false,"landing_page_url":"http://hdl.handle.net/10059/1830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400814","display_name":"Open Access Institutional Repository at Robert Gordon University (Robert Gordon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I522815984","host_organization_name":"Robert Gordon University","host_organization_lineage":["https://openalex.org/I522815984"],"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 publications"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1484575021","https://openalex.org/W1557074680","https://openalex.org/W1581881938","https://openalex.org/W1614151208","https://openalex.org/W1669912781","https://openalex.org/W1969192912","https://openalex.org/W1990190154","https://openalex.org/W2011316522","https://openalex.org/W2027823133","https://openalex.org/W2045411013","https://openalex.org/W2049633694","https://openalex.org/W2080209556","https://openalex.org/W2097333193","https://openalex.org/W2100873065","https://openalex.org/W2119788759","https://openalex.org/W2126385963","https://openalex.org/W2136583886","https://openalex.org/W2137320444","https://openalex.org/W2139042198","https://openalex.org/W2147308966","https://openalex.org/W2149041454","https://openalex.org/W2159083595","https://openalex.org/W2949496004","https://openalex.org/W3000429007","https://openalex.org/W4244760338"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W95465806","https://openalex.org/W2392004567","https://openalex.org/W2046296964","https://openalex.org/W2940029036","https://openalex.org/W4388292429","https://openalex.org/W4389670110","https://openalex.org/W2756595502","https://openalex.org/W2187546663","https://openalex.org/W2429057255"],"abstract_inverted_index":{"We":[0,88,149,200,239],"consider":[1],"the":[2,44,53,82,86,104,107,128,135,157,166,172,181,192,197,215,221,242],"problem":[3,16,38,71,129,158,167,198],"of":[4,23,33,85,99,106,162,206,223,244,252,270],"segmenting":[5],"text":[6,78,217],"documents":[7,51,101,151],"that":[8,29,46,94,160,211,226,257],"have":[9],"a":[10,15,19,37,73,90,97,187],"two-part":[11,91],"structure":[12],"such":[13,50,65,227],"as":[14,66,152],"part":[17,159,174],"and":[18,110,116,130,225,250,254,264],"solution":[20,45,131,173,182],"part.":[21,199],"Documents":[22],"this":[24],"genre":[25],"include":[26],"incident":[27],"reports":[28],"typically":[30],"involve":[31],"description":[32],"events":[34],"relating":[35],"to":[36,43,81,102,232,247],"followed":[39,170],"by":[40,171],"those":[41],"pertaining":[42],"was":[47],"tried.":[48],"Segmenting":[49],"into":[52],"component":[54],"two":[55,108],"parts":[56],"would":[57],"render":[58],"them":[59],"usable":[60],"in":[61,196,220,235],"knowledge":[62],"reuse":[63],"frameworks":[64],"Case-Based":[67],"Reasoning.":[68],"This":[69],"segmentation":[70,79,92,218],"presents":[72],"hard":[74],"case":[75],"for":[76,127],"traditional":[77],"due":[80],"lexical":[83],"inter-relatedness":[84,112,136],"segments.":[87],"develop":[89],"technique":[93,246,259],"can":[95],"harness":[96],"corpus":[98],"similar":[100],"model":[103,150,184,189],"behavior":[105],"segments":[109],"their":[111],"using":[113,142],"language":[114,125,168,183],"models":[115,118,126],"translation":[117,147,188],"respectively.":[119],"In":[120],"particular,":[121],"we":[122],"use":[123],"separate":[124],"segment":[132,138],"types,":[133],"whereas":[134],"between":[137],"types":[139,251],"is":[140,260],"modeled":[141],"an":[143,203],"IBM":[144],"Model":[145],"1":[146],"model.":[148],"being":[153],"generated":[154],"starting":[155],"from":[156,165,180,186],"comprises":[161],"words":[163,176,193],"sampled":[164,178],"model,":[169],"whose":[175],"are":[177],"either":[179],"or":[185],"conditioned":[190],"on":[191,208],"already":[194],"chosen":[195],"show,":[201],"through":[202],"extensive":[204],"set":[205],"experiments":[207],"real-world":[209],"data,":[210],"our":[212,245,258],"approach":[213],"outperforms":[214],"state-of-the-art":[216],"algorithms":[219],"accuracy":[222,229],"segmentation,":[224],"improved":[228,233],"translates":[230],"well":[231],"usability":[234],"Case-based":[236],"Reasoning":[237],"systems.":[238],"also":[240],"analyze":[241],"robustness":[243],"varying":[248],"amounts":[249,269],"noise":[253,262],"empirically":[255],"illustrate":[256],"quite":[261],"tolerant,":[263],"degrades":[265],"gracefully":[266],"with":[267],"increasing":[268],"noise.":[271]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}