{"id":"https://openalex.org/W2610077151","doi":null,"title":"Ubiquitous Usage of a French Large Corpus: Processing the Est Republicain Corpus","display_name":"Ubiquitous Usage of a French Large Corpus: Processing the Est Republicain Corpus","publication_year":2012,"publication_date":"2012-05-21","ids":{"openalex":"https://openalex.org/W2610077151","mag":"2610077151"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.383.4748","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.383.4748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2012/pdf/1130_Paper.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/A5010519567","display_name":"Djam\u00e9 Seddah","orcid":"https://orcid.org/0000-0003-0194-8197","observed_orcids":["https://orcid.org/0000-0003-0194-8197"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4387154366","display_name":"Universit\u00e9 Paris Diderot","ror":"https://ror.org/02n7qrg46","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241","https://openalex.org/I4387154366"]},{"id":"https://openalex.org/I4405261320","display_name":"Analyse Linguistique Profonde \u00e0 Grande Echelle","ror":"https://ror.org/0542cwx04","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I204730241","https://openalex.org/I4405261320"]},{"id":"https://openalex.org/I4405264515","display_name":"Paris-Sorbonne University","ror":"https://ror.org/025xed883","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081","https://openalex.org/I4405264515"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Djam\u00e9 Seddah","raw_affiliation_strings":["ALPAGE - Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing (Universit\u00e9 Paris Diderot, B\u00e2t. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt - France)","UP4 - Universit\u00e9 Paris-Sorbonne (1 rue Victor Cousin - 75005 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALPAGE - Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing (Universit\u00e9 Paris Diderot, B\u00e2t. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4387154366","https://openalex.org/I4405261320"]},{"raw_affiliation_string":"UP4 - Universit\u00e9 Paris-Sorbonne (1 rue Victor Cousin - 75005 Paris - France)","institution_ids":["https://openalex.org/I4405264515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056181885","display_name":"Marie Candito","orcid":"https://orcid.org/0000-0001-8306-4859","observed_orcids":["https://orcid.org/0000-0001-8306-4859"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4387154366","display_name":"Universit\u00e9 Paris Diderot","ror":"https://ror.org/02n7qrg46","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241","https://openalex.org/I4387154366"]},{"id":"https://openalex.org/I4405261320","display_name":"Analyse Linguistique Profonde \u00e0 Grande Echelle","ror":"https://ror.org/0542cwx04","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I204730241","https://openalex.org/I4405261320"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marie C","raw_affiliation_strings":["ALPAGE - Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing (Universit\u00e9 Paris Diderot, B\u00e2t. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALPAGE - Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing (Universit\u00e9 Paris Diderot, B\u00e2t. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4387154366","https://openalex.org/I4405261320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112901755","display_name":"Beno\u00eet Crabb\u00e9","orcid":"https://orcid.org/0000-0002-0821-0913","observed_orcids":["https://orcid.org/0000-0002-0821-0913"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4387154366","display_name":"Universit\u00e9 Paris Diderot","ror":"https://ror.org/02n7qrg46","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241","https://openalex.org/I4387154366"]},{"id":"https://openalex.org/I4405261320","display_name":"Analyse Linguistique Profonde \u00e0 Grande Echelle","ror":"https://ror.org/0542cwx04","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I204730241","https://openalex.org/I4405261320"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benoit Crabb\u00e9","raw_affiliation_strings":["ALPAGE - Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing (Universit\u00e9 Paris Diderot, B\u00e2t. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALPAGE - Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing (Universit\u00e9 Paris Diderot, B\u00e2t. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4387154366","https://openalex.org/I4405261320"]}]},{"author_position":"last","author":{"id":null,"display_name":"Enrique Henestroza Anguiano","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4387154366","display_name":"Universit\u00e9 Paris Diderot","ror":"https://ror.org/02n7qrg46","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241","https://openalex.org/I4387154366"]},{"id":"https://openalex.org/I4405261320","display_name":"Analyse Linguistique Profonde \u00e0 Grande Echelle","ror":"https://ror.org/0542cwx04","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I204730241","https://openalex.org/I4405261320"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Enrique Henestroza Anguiano","raw_affiliation_strings":["ALPAGE - Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing (Universit\u00e9 Paris Diderot, B\u00e2t. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALPAGE - Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing (Universit\u00e9 Paris Diderot, B\u00e2t. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4387154366","https://openalex.org/I4405261320"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1627,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79280813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"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":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/T10181","display_name":"Natural Language Processing Techniques","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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/french-language-resources","display_name":"French language resources","score":0.5699999928474426},{"id":"https://openalex.org/keywords/multiword-expressions","display_name":"multiword expressions","score":0.7059999704360962},{"id":"https://openalex.org/keywords/lemmatization","display_name":"lemmatization","score":0.8799999952316284},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.9929999709129333},{"id":"https://openalex.org/keywords/syntactic-analysis","display_name":"syntactic analysis","score":0.9300000071525574},{"id":"https://openalex.org/keywords/dependency-parsing","display_name":"dependency parsing","score":0.8579999804496765},{"id":"https://openalex.org/keywords/french-treebank","display_name":"French Treebank","score":0.8059999942779541},{"id":"https://openalex.org/keywords/word-clusters","display_name":"word clusters","score":0.7210000157356262},{"id":"https://openalex.org/keywords/statistical-parsing","display_name":"statistical parsing","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.864243745803833},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.8499026894569397},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.8283790349960327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7658531665802002},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7564857006072998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7354414463043213},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.5161069631576538},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4509167969226837},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.448515921831131},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41436901688575745},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1479295790195465},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0712645947933197},{"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:10.1.1.383.4748","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.383.4748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2012/pdf/1130_Paper.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00780899v1","doi":null,"is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00780899","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2012/pdf/1130_Paper.pdf","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1485490758","https://openalex.org/W1488557242","https://openalex.org/W1518867723","https://openalex.org/W1552062513","https://openalex.org/W1552442874","https://openalex.org/W1568793342","https://openalex.org/W1582588624","https://openalex.org/W1865928303","https://openalex.org/W1965897786","https://openalex.org/W1973346430","https://openalex.org/W1979711143","https://openalex.org/W2009468101","https://openalex.org/W2036239181","https://openalex.org/W2087165009","https://openalex.org/W2091835336","https://openalex.org/W2099896133","https://openalex.org/W2119518919","https://openalex.org/W2121227244","https://openalex.org/W2128634885","https://openalex.org/W2134899753","https://openalex.org/W2139621418","https://openalex.org/W2143413399","https://openalex.org/W2143541936","https://openalex.org/W2158049734","https://openalex.org/W2163568299","https://openalex.org/W2165131017","https://openalex.org/W2172242228","https://openalex.org/W2275355734","https://openalex.org/W2340896942","https://openalex.org/W2529763891","https://openalex.org/W2533653494","https://openalex.org/W2608077954"],"related_works":["https://openalex.org/W2251452258","https://openalex.org/W7096318894","https://openalex.org/W2400878268","https://openalex.org/W3082120123","https://openalex.org/W2103684207","https://openalex.org/W4406123353","https://openalex.org/W1973346430","https://openalex.org/W7066977246","https://openalex.org/W947942229","https://openalex.org/W7097339406"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,10],"introduce":[4],"a":[5,18,38],"set":[6],"of":[7,22,37,42,48,58,70,124,127,137],"resources":[8,33,100,129],"that":[9,84],"have":[11,85],"derived":[12,99],"from":[13,141],"the":[14,35,43,59,95,109,115,125,135,142],"EST":[15,44,116],"R\u00c9PUBLICAIN":[16,45,117],"CORPUS,":[17],"large,":[19],"freely-available":[20],"collection":[21],"regional":[23],"newspaper":[24],"articles":[25],"in":[26,130,133],"French,":[27],"totaling":[28],"150":[29],"million":[30],"words.":[31],"Our":[32,98],"are":[34,101],"result":[36],"full":[39],"NLP":[40],"treatment":[41],"CORPUS:":[46],"handling":[47],"multi-word":[49],"expressions,":[50],"lemmatization,":[51],"part-of-speech":[52],"tagging,":[53,76],"and":[54,74,78,105],"syntactic":[55],"parsing.":[56,151],"Processing":[57],"corpus":[60,143],"is":[61],"carried":[62],"out":[63],"using":[64],"statistical":[65,150],"machine-learning":[66],"approaches-":[67],"joint":[68],"model":[69],"data":[71,147],"driven":[72],"lemmatization":[73],"partof-speech":[75],"PCFG-LA":[77],"dependency":[79],"based":[80],"models":[81],"for":[82,114,149],"parsing-":[83],"been":[86],"shown":[87],"to":[88,108,144],"achieve":[89],"state-of-the-art":[90],"performance":[91],"when":[92],"evaluated":[93],"on":[94],"French":[96],"Treebank.":[97],"made":[102],"freely":[103],"available,":[104],"released":[106],"according":[107],"original":[110],"Creative":[111],"Common":[112],"license":[113],"CORPUS.":[118],"We":[119],"additionally":[120],"provide":[121],"an":[122],"overview":[123],"use":[126,136],"these":[128],"various":[131],"applications,":[132],"particular":[134],"generated":[138],"word":[139],"clusters":[140],"alleviate":[145],"lexical":[146],"sparseness":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2017-05-05T00:00:00"}