{"id":"https://openalex.org/W2182983245","doi":"https://doi.org/10.20381/ruor-6645","title":"Topical Structure in Long Informal Documents","display_name":"Topical Structure in Long Informal Documents","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2182983245","doi":"https://doi.org/10.20381/ruor-6645","mag":"2182983245"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.672.1398","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.672.1398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.caiac.ca/sites/default/files/publications/5_Kazantseva_PhD_thesis.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20381/ruor-6645","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065770950","display_name":"Anna Kazantseva","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kazantseva, Anna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5065770950"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2982,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68331034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5580999851226807,"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":0.5580999851226807,"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":0.21889999508857727,"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":0.13650000095367432,"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/topical-structure","display_name":"topical structure","score":0.824999988079071},{"id":"https://openalex.org/keywords/discourse-structure","display_name":"discourse structure","score":0.781000018119812},{"id":"https://openalex.org/keywords/factor-graphs","display_name":"factor graphs","score":0.7789999842643738},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"affinity propagation","score":0.9430000185966492},{"id":"https://openalex.org/keywords/extractive-summarization","display_name":"extractive summarization","score":0.6740000247955322},{"id":"https://openalex.org/keywords/literary-works","display_name":"literary works","score":0.5080000162124634},{"id":"https://openalex.org/keywords/speech-transcripts","display_name":"speech transcripts","score":0.9909999966621399},{"id":"https://openalex.org/keywords/annotated-corpora","display_name":"annotated corpus","score":0.6340000033378601},{"id":"https://openalex.org/keywords/manual-annotation","display_name":"manual annotation","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6875177025794983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6637879014015198},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6420468091964722},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5768676400184631},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5659461617469788},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4761888086795807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4374561905860901},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3409286141395569},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10616731643676758}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.672.1398","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.672.1398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.caiac.ca/sites/default/files/publications/5_Kazantseva_PhD_thesis.pdf","raw_type":"text"},{"id":"pmh:oai:ruor.uottawa.ca:10393/31612","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10393/31612","pdf_url":null,"source":{"id":"https://openalex.org/S4306400902","display_name":"uO Research (University of Ottawa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I153718931","host_organization_name":"University of Ottawa","host_organization_lineage":["https://openalex.org/I153718931"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"doi:10.20381/ruor-6645","doi":"https://doi.org/10.20381/ruor-6645","is_oa":true,"landing_page_url":"https://doi.org/10.20381/ruor-6645","pdf_url":null,"source":{"id":"https://openalex.org/S7407053184","display_name":"University of Ottawa - Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2182983245","doi":null,"is_oa":false,"landing_page_url":"http://ruor.uottawa.ca/bitstream/10393/31612/1/Kazantseva_Anna_2014_thesis.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.20381/ruor-6645","doi":"https://doi.org/10.20381/ruor-6645","is_oa":true,"landing_page_url":"https://doi.org/10.20381/ruor-6645","pdf_url":null,"source":{"id":"https://openalex.org/S7407053184","display_name":"University of Ottawa - Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":148,"referenced_works":["https://openalex.org/W14379156","https://openalex.org/W36731393","https://openalex.org/W46503584","https://openalex.org/W60686164","https://openalex.org/W103216324","https://openalex.org/W143713808","https://openalex.org/W265278043","https://openalex.org/W580328291","https://openalex.org/W590358987","https://openalex.org/W648947103","https://openalex.org/W966751452","https://openalex.org/W1481431397","https://openalex.org/W1483074234","https://openalex.org/W1484886975","https://openalex.org/W1484951490","https://openalex.org/W1486393111","https://openalex.org/W1486798440","https://openalex.org/W1488461535","https://openalex.org/W1489616935","https://openalex.org/W1491947308","https://openalex.org/W1495981708","https://openalex.org/W1525245406","https://openalex.org/W1532156013","https://openalex.org/W1556417835","https://openalex.org/W1557074680","https://openalex.org/W1565981144","https://openalex.org/W1566301929","https://openalex.org/W1568886291","https://openalex.org/W1574440611","https://openalex.org/W1576213419","https://openalex.org/W1580653169","https://openalex.org/W1586232984","https://openalex.org/W1587116172","https://openalex.org/W1591607137","https://openalex.org/W1597655096","https://openalex.org/W1600133633","https://openalex.org/W1601482488","https://openalex.org/W1626945812","https://openalex.org/W1632114991","https://openalex.org/W1663973292","https://openalex.org/W1748393397","https://openalex.org/W1777978449","https://openalex.org/W1787105636","https://openalex.org/W1794961931","https://openalex.org/W1828401780","https://openalex.org/W1857121649","https://openalex.org/W1858830546","https://openalex.org/W1862888253","https://openalex.org/W1880262756","https://openalex.org/W1968340857","https://openalex.org/W1968596497","https://openalex.org/W1975579663","https://openalex.org/W1983578042","https://openalex.org/W1983814883","https://openalex.org/W1988627755","https://openalex.org/W1990070937","https://openalex.org/W1990689692","https://openalex.org/W1994448786","https://openalex.org/W2002664886","https://openalex.org/W2005313804","https://openalex.org/W2010058467","https://openalex.org/W2015466640","https://openalex.org/W2015933299","https://openalex.org/W2017776283","https://openalex.org/W2027823133","https://openalex.org/W2038014947","https://openalex.org/W2041986487","https://openalex.org/W2044491728","https://openalex.org/W2044599851","https://openalex.org/W2045738181","https://openalex.org/W2046085661","https://openalex.org/W2046416673","https://openalex.org/W2053154970","https://openalex.org/W2053569739","https://openalex.org/W2066636486","https://openalex.org/W2069684104","https://openalex.org/W2072841814","https://openalex.org/W2084776073","https://openalex.org/W2084909186","https://openalex.org/W2096765155","https://openalex.org/W2104573870","https://openalex.org/W2106695994","https://openalex.org/W2106918957","https://openalex.org/W2108212867","https://openalex.org/W2109209896","https://openalex.org/W2111535382","https://openalex.org/W2117853077","https://openalex.org/W2118612506","https://openalex.org/W2120779048","https://openalex.org/W2128347080","https://openalex.org/W2128709346","https://openalex.org/W2133280805","https://openalex.org/W2133943399","https://openalex.org/W2135336649","https://openalex.org/W2135909747","https://openalex.org/W2137320444","https://openalex.org/W2137813581","https://openalex.org/W2138623081","https://openalex.org/W2140945425","https://openalex.org/W2141403362","https://openalex.org/W2141766660","https://openalex.org/W2142243548","https://openalex.org/W2145211186","https://openalex.org/W2147880316","https://openalex.org/W2148727093","https://openalex.org/W2151295812","https://openalex.org/W2153222072","https://openalex.org/W2154407881","https://openalex.org/W2154593091","https://openalex.org/W2154652894","https://openalex.org/W2156094048","https://openalex.org/W2158794898","https://openalex.org/W2158889760","https://openalex.org/W2159083595","https://openalex.org/W2159637096","https://openalex.org/W2160039585","https://openalex.org/W2161793958","https://openalex.org/W2163814903","https://openalex.org/W2164777277","https://openalex.org/W2165232124","https://openalex.org/W2165887782","https://openalex.org/W2166776180","https://openalex.org/W2166957049","https://openalex.org/W2167702024","https://openalex.org/W2169384404","https://openalex.org/W2170516265","https://openalex.org/W2176475152","https://openalex.org/W2243879816","https://openalex.org/W2251216540","https://openalex.org/W2251460488","https://openalex.org/W2251717670","https://openalex.org/W2277978090","https://openalex.org/W2296730072","https://openalex.org/W2321031999","https://openalex.org/W2326936009","https://openalex.org/W2327401115","https://openalex.org/W2341007060","https://openalex.org/W2442495973","https://openalex.org/W2490708903","https://openalex.org/W2498966852","https://openalex.org/W2506900267","https://openalex.org/W2725860187","https://openalex.org/W2740756483","https://openalex.org/W2918065816","https://openalex.org/W2963703672","https://openalex.org/W3011488282","https://openalex.org/W3083626077","https://openalex.org/W3177313737"],"related_works":["https://openalex.org/W2017776283","https://openalex.org/W2118515079","https://openalex.org/W2250730265","https://openalex.org/W1673478674","https://openalex.org/W2108824730","https://openalex.org/W2402528451","https://openalex.org/W90119049","https://openalex.org/W3173492436","https://openalex.org/W2128709346","https://openalex.org/W2067002391"],"abstract_inverted_index":{"This":[0],"dissertation":[1,277],"describes":[2],"a":[3,48,75,112,115,123,128,132,168,172,175,214,233],"research":[4],"project":[5],"concerned":[6],"with":[7,29,82,282],"establishing":[8],"the":[9,54,98,109,180,183,188,197,207,327,337],"topical":[10,118,163,236,305,320],"structure":[11,110,321],"of":[12,36,50,56,94,97,102,111,117,135,147,154,182,196,209,225,286,297,304,329,340],"long":[13,40],"informal":[14],"documents.":[15,287],"In":[16,70,159,185,199,288],"this":[17,71,186,276,341],"research,":[18],"we":[19,73,105,205,300],"place":[20],"special":[21],"emphasis":[22,84],"on":[23,85,127,144,257],"literary":[24,298],"data,":[25,299],"but":[26],"also":[27],"work":[28],"speech":[30,266],"transcripts":[31],"and":[32,90,212,309,332],"several":[33],"other":[34],"types":[35,285],"data.":[37],"It":[38],"has":[39],"been":[41],"acknowledged":[42],"that":[43,68,125,177,259],"discourse":[44,80,103],"is":[45,63,156,165,229,239,278,317],"more":[46],"than":[47],"sequence":[49],"sentences":[51],"but,":[52],"for":[53,319,334],"purposes":[55],"many":[57,99],"Natural":[58],"Language":[59],"Processing":[60],"tasks,":[61],"it":[62,86,228],"often":[64],"modelled":[65],"exactly":[66],"in":[67,275,314],"way.":[69],"dissertation,":[72],"propose":[74],"practical":[76],"approach":[77],"to":[78,107,201,220,290],"modelling":[79],"structure,":[81,104,263],"an":[83,192],"being":[87,232],"computationally":[88],"feasible":[89],"easily":[91],"applicable.":[92],"Instead":[93],"following":[95],"one":[96,307,310],"linguistic":[100],"theories":[101],"attempt":[106],"model":[108,273,328],"document":[113,313],"as":[114,265],"tree":[116],"segments.":[119],"Each":[120,137,312],"segment":[121,164,169],"encapsulates":[122],"span":[124,138],"concentrates":[126],"particular":[129],"topic":[130],"at":[131],"certain":[133],"level":[134,153],"granularity.":[136],"can":[139],"be":[140],"further":[141],"sub-segmented":[142],"based":[143],"finer":[145],"fluctuations":[146],"topic.":[148],"The":[149,243,272,325],"lowest":[150],"(most":[151],"refined)":[152],"segmentation":[155,223,238,331,335],"individual":[157],"paragraphs.":[158],"our":[160],"model,":[161],"each":[162],"described":[166,274],"by":[167,322],"centre":[170],"--":[171],"sentence":[173],"or":[174,270],"paragraph":[176],"best":[178],"captures":[179],"contents":[181],"segment.":[184],"manner,":[187],"segmenter":[189],"effectively":[190],"builds":[191],"extractive":[193],"hierarchical":[194,222,330],"outline":[195],"document.":[198],"order":[200,289],"achieve":[202],"these":[203,315],"goals,":[204],"use":[206],"framework":[208],"factor":[210],"graphs":[211],"modify":[213],"recent":[215],"clustering":[216],"algorithm,":[217],"Affinity":[218],"Propagation,":[219],"perform":[221,249],"instead":[224],"clustering.":[226],"While":[227],"far":[230],"from":[231],"solved":[234],"problem,":[235],"text":[237],"not":[240],"uncharted":[241],"territory.":[242],"methods":[244],"developed":[245],"so":[246],"far,":[247],"however,":[248],"least":[250],"well":[251],"where":[252],"they":[253],"are":[254,336],"most":[255],"needed:":[256],"documents":[258],"lack":[260],"rigid":[261],"formal":[262],"such":[264,284],"transcripts,":[267],"personal":[268],"correspondence":[269],"literature.":[271],"geared":[279],"towards":[280],"dealing":[281],"just":[283],"study":[291],"how":[292],"people":[293],"create":[294],"similar":[295],"models":[296],"built":[301],"two":[302],"corpora":[303,316],"segmentations,":[306],"flat":[308],"hierarchical.":[311],"annotated":[318],"3-6":[323],"people.":[324],"corpora,":[326],"software":[333],"main":[338],"contributions":[339],"work.":[342]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}