{"id":"https://openalex.org/W2952391587","doi":"https://doi.org/10.18653/v1/p19-1133","title":"Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution Losses","display_name":"Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution Losses","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952391587","doi":"https://doi.org/10.18653/v1/p19-1133","mag":"2952391587"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1133","pdf_url":"https://www.aclweb.org/anthology/P19-1133.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":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1133.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054258348","display_name":"\u00c9tienne Simon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"\u00c9tienne Simon","raw_affiliation_strings":["MLIA - Machine Learning and Information Access (France)"],"affiliations":[{"raw_affiliation_string":"MLIA - Machine Learning and Information Access (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044389669","display_name":"Vincent Guigue","orcid":"https://orcid.org/0000-0002-1450-5566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Guigue","raw_affiliation_strings":["MLIA - Machine Learning and Information Access (France)"],"affiliations":[{"raw_affiliation_string":"MLIA - Machine Learning and Information Access (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086752907","display_name":"Benjamin Piwowarski","orcid":"https://orcid.org/0000-0001-6792-3262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Piwowarski","raw_affiliation_strings":["BD - Bases de Donn\u00e9es (France)"],"affiliations":[{"raw_affiliation_string":"BD - Bases de Donn\u00e9es (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054258348"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4725,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94169067,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1378","last_page":"1387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9975000023841858,"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/discriminative-model","display_name":"Discriminative model","score":0.9486116170883179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7226372957229614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6910144090652466},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6451452374458313},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5967941880226135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5619907975196838},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5456519722938538},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5063010454177856},{"id":"https://openalex.org/keywords/skewness","display_name":"Skewness","score":0.493307501077652},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.46817129850387573},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4427143931388855},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.44221869111061096},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42086061835289},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.41385120153427124},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26467564702033997},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.21042385697364807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17017266154289246},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11836409568786621}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9486116170883179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7226372957229614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6910144090652466},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6451452374458313},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5967941880226135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5619907975196838},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5456519722938538},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5063010454177856},{"id":"https://openalex.org/C122342681","wikidata":"https://www.wikidata.org/wiki/Q330828","display_name":"Skewness","level":2,"score":0.493307501077652},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.46817129850387573},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4427143931388855},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.44221869111061096},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42086061835289},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.41385120153427124},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26467564702033997},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.21042385697364807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17017266154289246},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11836409568786621}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p19-1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1133","pdf_url":"https://www.aclweb.org/anthology/P19-1133.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-02318233v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02318233","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.acl2019.org","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1133","pdf_url":"https://www.aclweb.org/anthology/P19-1133.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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952391587.pdf","grobid_xml":"https://content.openalex.org/works/W2952391587.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W115166160","https://openalex.org/W174427690","https://openalex.org/W205829674","https://openalex.org/W1493490255","https://openalex.org/W2000411838","https://openalex.org/W2030408698","https://openalex.org/W2038880450","https://openalex.org/W2094728533","https://openalex.org/W2107598941","https://openalex.org/W2123143128","https://openalex.org/W2127426251","https://openalex.org/W2127978399","https://openalex.org/W2132679783","https://openalex.org/W2138615112","https://openalex.org/W2148932298","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2251079237","https://openalex.org/W2251135946","https://openalex.org/W2251913848","https://openalex.org/W2252136820","https://openalex.org/W2467240462","https://openalex.org/W2515462165","https://openalex.org/W2785611959","https://openalex.org/W2896457183","https://openalex.org/W2963341956","https://openalex.org/W3158986179","https://openalex.org/W4254240410","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W4241564561"],"abstract_inverted_index":{"Unsupervised":[0],"relation":[1,67],"extraction":[2],"aims":[3],"at":[4],"extracting":[5],"relations":[6,81],"between":[7],"entities":[8],"in":[9,84],"text.":[10],"Previous":[11],"unsupervised":[12],"approaches":[13],"are":[14,38,49,82],"either":[15],"generative":[16],"or":[17],"discriminative.":[18],"In":[19],"a":[20,57,66,71,74],"supervised":[21],"setting,":[22],"discriminative":[23,92],"approaches,":[24],"such":[25],"as":[26],"deep":[27,100],"neural":[28,101],"network":[29],"classifiers,":[30],"have":[31],"demonstrated":[32],"substantial":[33],"improvement.":[34],"However,":[35],"these":[36],"models":[37],"hard":[39],"to":[40,64,98],"train":[41,99],"without":[42],"supervision,":[43],"and":[44,73,95],"the":[45,62,89,108],"currently":[46],"proposed":[47],"solutions":[48],"unstable.":[50],"To":[51],"overcome":[52],"this":[53],"limitation,":[54],"we":[55],"introduce":[56],"skewness":[58],"loss":[59,77],"which":[60],"encourages":[61],"classifier":[63],"predict":[65],"with":[68],"confidence":[69],"given":[70],"sentence,":[72],"distribution":[75],"distance":[76],"enforcing":[78],"that":[79],"all":[80],"predicted":[83],"average.":[85],"These":[86],"losses":[87],"improve":[88],"performance":[90],"of":[91,107],"based":[93],"models,":[94],"enable":[96],"us":[97],"networks":[102],"satisfactorily,":[103],"surpassing":[104],"current":[105],"state":[106],"art":[109],"on":[110],"three":[111],"different":[112],"datasets.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}