{"id":"https://openalex.org/W2461928176","doi":null,"title":"Automatic Discourse Segmentation using Neural Networks","display_name":"Automatic Discourse Segmentation using Neural Networks","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2461928176","mag":"2461928176"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.3515","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.3515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cimec.unitn.it/events/decalog/pdf/decalog_subba.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5113753370","display_name":"Rajen Subba","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajen Subba","raw_affiliation_strings":["University of Illinois at #TAB#Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at #TAB#Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055258367","display_name":"Barbara Di Eugenio","orcid":"https://orcid.org/0000-0003-1706-2577","observed_orcids":["https://orcid.org/0000-0003-1706-2577"]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Di Eugenio","raw_affiliation_strings":["University of Illinois at #TAB#Chicago"],"raw_orcid":"https://orcid.org/0000-0003-1706-2577","affiliations":[{"raw_affiliation_string":"University of Illinois at #TAB#Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":1.7901,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.87784596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":98},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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":0.9951000213623047,"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":0.0012000000569969416,"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/T12031","display_name":"Speech and dialogue systems","score":0.0008999999845400453,"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/discourse-segmentation","display_name":"discourse segmentation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/elementary-discourse-units","display_name":"elementary discourse units","score":0.9990000128746033},{"id":"https://openalex.org/keywords/discourse-parsing","display_name":"discourse parsing","score":0.5809999704360962},{"id":"https://openalex.org/keywords/part-of-speech-tags","display_name":"part-of-speech tags","score":0.824999988079071},{"id":"https://openalex.org/keywords/syntactic-information","display_name":"syntactic information","score":0.8939999938011169},{"id":"https://openalex.org/keywords/discourse-cues","display_name":"discourse cues","score":0.9909999966621399},{"id":"https://openalex.org/keywords/punctuation","display_name":"punctuation","score":0.9390000104904175}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9544399976730347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055208921432495},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7760473489761353},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7410026788711548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7205654978752136},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.670617938041687},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.5203577876091003},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48972633481025696},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46054500341415405},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.45897406339645386},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.431831955909729},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4021635055541992},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.3515","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.3515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cimec.unitn.it/events/decalog/pdf/decalog_subba.pdf","raw_type":"text"},{"id":"mag:2461928176","doi":null,"is_oa":false,"landing_page_url":"http://nlp.cs.uic.edu/PS-papers/decalog_subba.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":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W174120577","https://openalex.org/W1597655096","https://openalex.org/W2154407881","https://openalex.org/W2729906263","https://openalex.org/W3171719338"],"related_works":["https://openalex.org/W2964727359","https://openalex.org/W6939458845","https://openalex.org/W7098893233","https://openalex.org/W1517148511","https://openalex.org/W3214384030","https://openalex.org/W7096246834","https://openalex.org/W1567616047","https://openalex.org/W2130867674","https://openalex.org/W3091951012","https://openalex.org/W3005536492"],"abstract_inverted_index":{"Discourse":[0,136],"segmentation":[1,24],"is":[2,123,139,192,231],"the":[3,32,43,64,67,74,93,97,104,119,162,184,188],"task":[4,174],"of":[5,10,149,187,213],"determining":[6],"minimal":[7],"non-overlapping":[8],"units":[9,15],"discourse":[11,14,27,158,168,207,224,235,240],"called":[12],"elementary":[13,157],"(EDUs).":[16],"It":[17],"can":[18,170],"be":[19,171,181,194],"further":[20,124],"subdivided":[21],"into":[22,126],"sentence":[23,40,110,144],"and":[25,41,132,226],"sentence-level":[26],"segmentation.":[28],"This":[29],"paper":[30],"addresses":[31],"latter,":[33],"more":[34],"challenging":[35],"subtask,":[36],"which":[37],"takes":[38],"a":[39,109,112,165,172,199,206,234],"outputs":[42],"EDUs":[44],"for":[45,73,103,203],"that":[46,57,86,191,237],"particular":[47,189],"sentence.":[48],"(1)":[49],"Saturday,":[50,77],"he":[51,58,78,87],"amended":[52,79],"his":[53,80],"remarks":[54,81],"to":[55,61,83,90,153,161,180,193,218,232],"say":[56,84],"would":[59,88,178],"continue":[60,89],"abide":[62,91],"by":[63,92],"cease-fire":[65,94],"if":[66,96],"U.S.":[68,98],"ends":[69,99],"its":[70,100],"financial":[71,101],"support":[72,102],"Contras.":[75,105],"(1a)":[76],"(1b)":[82],"(1c)":[85,131],"(1d)":[95,133],"In":[106],"example":[107],"(1),":[108],"from":[111,118,209],"Wall":[113],"Street":[114],"Journal":[115],"article":[116],"taken":[117],"Penn":[120],"TreeBank":[121],"corpus":[122,212],"segmented":[125,214],"four":[127],"EDUs,":[128],"(1a),":[129],"(1b),":[130],"(RST,":[134],"2002).":[135],"segmentation,":[137],"clearly,":[138],"not":[140],"as":[141,143],"easy":[142],"boundary":[145],"detection.":[146],"The":[147],"lack":[148],"consensus":[150],"with":[151],"regards":[152],"what":[154],"constitutes":[155],"an":[156,210],"unit":[159],"adds":[160],"difficulty.":[163],"Building":[164],"rule":[166],"based":[167,182],"segmenter":[169,208],"tedious":[173],"since":[175],"these":[176],"rules":[177],"have":[179],"on":[183],"underlying":[185,211],"grammar":[186],"parser":[190,236],"used.":[195],"Therefore,":[196],"we":[197],"adopted":[198],"neural":[200],"network":[201],"model":[202],"automatically":[204],"building":[205],"text.":[215],"We":[216],"chose":[217],"use":[219],"part-of-speech":[220],"tags,":[221],"syntactic":[222],"information,":[223],"cues":[225],"punctuation.":[227],"Our":[228],"ultimate":[229],"goal":[230],"build":[233],"uses":[238],"this":[239],"segmenter.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-07-22T00:00:00"}