{"id":"https://openalex.org/W2950037760","doi":"https://doi.org/10.18653/v1/p19-1061","title":"Data Programming for Learning Discourse Structure","display_name":"Data Programming for Learning Discourse Structure","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2950037760","doi":"https://doi.org/10.18653/v1/p19-1061","mag":"2950037760"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1061","pdf_url":"https://www.aclweb.org/anthology/P19-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1061.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034910386","display_name":"Sonia Badene","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210149153","display_name":"Linagora (France)","ror":"https://ror.org/03pd1sq22","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210149153"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sonia Badene","raw_affiliation_strings":["IRIT,","Linagora,"],"affiliations":[{"raw_affiliation_string":"IRIT,","institution_ids":["https://openalex.org/I4210119061"]},{"raw_affiliation_string":"Linagora,","institution_ids":["https://openalex.org/I4210149153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017500501","display_name":"Kate Thompson","orcid":"https://orcid.org/0000-0003-0738-0205"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I4210098964","display_name":"Toulouse Mathematics Institute","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210098964"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kate Thompson","raw_affiliation_strings":["IRIT,","Universit Toulouse III & CNRS"],"affiliations":[{"raw_affiliation_string":"IRIT,","institution_ids":["https://openalex.org/I4210119061"]},{"raw_affiliation_string":"Universit Toulouse III & CNRS","institution_ids":["https://openalex.org/I134560555","https://openalex.org/I4210098964","https://openalex.org/I17866349","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056533367","display_name":"Jean-Pierre Lorr\u00e9","orcid":"https://orcid.org/0000-0002-1929-0728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Pierre Lorr\u00e9","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019863253","display_name":"Nicholas Asher","orcid":"https://orcid.org/0000-0002-7689-8246"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I4210098964","display_name":"Toulouse Mathematics Institute","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210098964"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Asher","raw_affiliation_strings":["IRIT,","Universit Toulouse III & CNRS"],"affiliations":[{"raw_affiliation_string":"IRIT,","institution_ids":["https://openalex.org/I4210119061"]},{"raw_affiliation_string":"Universit Toulouse III & CNRS","institution_ids":["https://openalex.org/I134560555","https://openalex.org/I4210098964","https://openalex.org/I17866349","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034910386"],"corresponding_institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I4210149153"],"apc_list":null,"apc_paid":null,"fwci":1.1201,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83547556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"640","last_page":"645"},"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/T12031","display_name":"Speech and dialogue systems","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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/heuristics","display_name":"Heuristics","score":0.8666748404502869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7950351238250732},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6658938527107239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5932450294494629},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5220310688018799},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5204627513885498},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5116181969642639},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.50299471616745},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4286145269870758},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34660112857818604},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08826029300689697}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8666748404502869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950351238250732},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6658938527107239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5932450294494629},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5220310688018799},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5204627513885498},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5116181969642639},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.50299471616745},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4286145269870758},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34660112857818604},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08826029300689697},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p19-1061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1061","pdf_url":"https://www.aclweb.org/anthology/P19-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02393478v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02393478","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computational LInguistics (ACL), Jul 2019, Florence, Italy. pp.640-645, ⟨10.18653/v1/P19-1061⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1061","pdf_url":"https://www.aclweb.org/anthology/P19-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950037760.pdf","grobid_xml":"https://content.openalex.org/works/W2950037760.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1572063013","https://openalex.org/W1574440611","https://openalex.org/W1665214252","https://openalex.org/W2097700060","https://openalex.org/W2107598941","https://openalex.org/W2158211888","https://openalex.org/W2158570207","https://openalex.org/W2251293245","https://openalex.org/W2251454145","https://openalex.org/W2251618894","https://openalex.org/W2404161646","https://openalex.org/W2469477431","https://openalex.org/W2546302380","https://openalex.org/W2565349465","https://openalex.org/W2579198228","https://openalex.org/W2746791238","https://openalex.org/W2769041395","https://openalex.org/W2795439700","https://openalex.org/W2809742878","https://openalex.org/W2959716049","https://openalex.org/W2962915384","https://openalex.org/W2964121744","https://openalex.org/W3125937743"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W2593887162","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W3014948380","https://openalex.org/W1493875009","https://openalex.org/W2751624083"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,11,23,41,48,52,84,141,144,163],"advantages":[4],"and":[5],"limits":[6],"of":[7,13,47,72,79,86,89,103,143],"data":[8,18,32,74,81],"programming":[9,19],"for":[10,96],"task":[12],"learning":[14,160],"discourse":[15,104,114,129],"structure.":[16,130],"The":[17],"paradigm":[20],"implemented":[21],"in":[22,106,120,123],"Snorkel":[24,136],"framework":[25],"allows":[26],"a":[27,61,69,76,87,112,121,127],"user":[28],"to":[29,67,93,117,125,140,162],"label":[30],"training":[31,53,80],"using":[33,60,135],"expert-composed":[34],"heuristics,":[35,145],"which":[36,107],"are":[37,57],"then":[38],"transformed":[39],"via":[40],"\"generative":[42],"step\"":[43],"into":[44],"probability":[45],"distributions":[46],"class":[49],"labels":[50],"given":[51,113],"candidates.":[54],"These":[55],"results":[56],"later":[58],"generalized":[59],"discriminative":[62],"model.":[63],"Snorkel's":[64],"attractive":[65],"promise":[66],"create":[68],"large":[70],"amount":[71],"annotated":[73],"from":[75],"smaller":[77],"set":[78,88],"by":[82],"unifying":[83],"output":[85],"heuristics":[90],"has":[91],"yet":[92],"be":[94,153],"used":[95],"computationally":[97],"difficult":[98],"tasks,":[99],"such":[100],"as":[101],"that":[102,148],"attachment,":[105],"one":[108],"must":[109],"decide":[110],"where":[111],"unit":[115],"attaches":[116],"other":[118],"units":[119],"text":[122],"order":[124],"form":[126],"coherent":[128],"Although":[131],"approaching":[132],"this":[133],"problem":[134],"requires":[137],"significant":[138],"modifications":[139],"structure":[142],"we":[146],"show":[147],"weak":[149],"supervision":[150],"methods":[151],"can":[152],"more":[154],"than":[155],"competitive":[156],"with":[157],"classical":[158],"supervised":[159],"approaches":[161],"attachment":[164],"problem.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-03T00:53:05.648605","created_date":"2025-10-10T00:00:00"}