{"id":"https://openalex.org/W1014376541","doi":null,"title":"Computational Linguistics (2012)\" The French Social Media Bank: a Treebank of Noisy User Generated Content","display_name":"Computational Linguistics (2012)\" The French Social Media Bank: a Treebank of Noisy User Generated Content","publication_year":2012,"publication_date":"2012-12-08","ids":{"openalex":"https://openalex.org/W1014376541","mag":"1014376541"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.379.2720","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.379.2720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/C/C12/C12-1149.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00780895","any_repository_has_fulltext":true},"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":"Seddah, Djam\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)","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/A5077663332","display_name":"Beno\u00eet Sagot","orcid":"https://orcid.org/0000-0002-0107-8526","observed_orcids":["https://orcid.org/0000-0002-0107-8526"]},"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":"Sagot, Beno\u00eet","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/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":"Candito, Marie","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/A5069735344","display_name":"Virginie Mouilleron","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":"Mouilleron, Virginie","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":"https://openalex.org/A5007076294","display_name":"Vanessa Combet","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":"Combet, Vanessa","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":3.7725,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.93055591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":9.999999747378752e-05,"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/treebank","display_name":"treebank","score":0.6259999871253967},{"id":"https://openalex.org/keywords/user-generated-content","display_name":"user-generated content","score":0.9890000224113464},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.8009999990463257},{"id":"https://openalex.org/keywords/noisy-text","display_name":"noisy text","score":0.6990000009536743},{"id":"https://openalex.org/keywords/morphologically-rich-languages","display_name":"morphologically rich languages","score":0.906000018119812},{"id":"https://openalex.org/keywords/french-language","display_name":"French language","score":0.6119999885559082},{"id":"https://openalex.org/keywords/constituency-parsing","display_name":"constituency parsing","score":0.7089999914169312},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.9800000190734863},{"id":"https://openalex.org/keywords/annotation-methods","display_name":"annotation methodology","score":0.5339999794960022},{"id":"https://openalex.org/keywords/web-2-0","display_name":"Web 2.0","score":0.8669999837875366}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9774526953697205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8793781995773315},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7585205435752869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6418721079826355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6213580369949341},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5252444744110107},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.4177597165107727},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20057833194732666}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.379.2720","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.379.2720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/C/C12/C12-1149.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.382.3614","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.382.3614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/78/08/95/PDF/coling2012.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00780895v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00780895","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"COLING 2012 - 24th International Conference on Computational Linguistics, Kay, Martin and Boitet, Christian, Dec 2012, Mumbai, India","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00780895v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00780895","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"COLING 2012 - 24th International Conference on Computational Linguistics, Kay, Martin and Boitet, Christian, Dec 2012, Mumbai, India","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W98423455","https://openalex.org/W108437174","https://openalex.org/W199541590","https://openalex.org/W1518819622","https://openalex.org/W1518867723","https://openalex.org/W1552062513","https://openalex.org/W1582588624","https://openalex.org/W1586073462","https://openalex.org/W1588971009","https://openalex.org/W1818857488","https://openalex.org/W1865928303","https://openalex.org/W1965897786","https://openalex.org/W1973346430","https://openalex.org/W2009468101","https://openalex.org/W2051840895","https://openalex.org/W2054762263","https://openalex.org/W2066376430","https://openalex.org/W2091835336","https://openalex.org/W2101461018","https://openalex.org/W2105103433","https://openalex.org/W2109000768","https://openalex.org/W2119518919","https://openalex.org/W2121912514","https://openalex.org/W2127147316","https://openalex.org/W2134899753","https://openalex.org/W2138382875","https://openalex.org/W2139621418","https://openalex.org/W2149709850","https://openalex.org/W2157765050","https://openalex.org/W2163568299","https://openalex.org/W2172242228","https://openalex.org/W2529763891","https://openalex.org/W2533653494","https://openalex.org/W2618389316"],"related_works":["https://openalex.org/W7096211354","https://openalex.org/W2209845672","https://openalex.org/W93459206","https://openalex.org/W2500054912","https://openalex.org/W2251037071","https://openalex.org/W7160245132","https://openalex.org/W7095354056","https://openalex.org/W2159528551","https://openalex.org/W2167193140","https://openalex.org/W2575884139"],"abstract_inverted_index":{"In":[0,45],"recent":[1],"years,":[2],"statistical":[3,173],"parsers":[4,29],"have":[5,16,107],"reached":[6],"high":[7,146,191],"performance":[8],"levels":[9],"on":[10,20,100,185],"well-edited":[11],"texts.":[12,187],"Domain":[13],"adaptation":[14],"techniques":[15],"improved":[17],"parsing":[18,175],"results":[19,184],"text":[21],"genres":[22],"differing":[23],"from":[24,97,135],"the":[25,46,48,57,109,114,158,190],"journalistic":[26],"data":[27,72,141,198],"most":[28,90],"are":[30,86,178],"trained":[31],"on.":[32],"However,":[33],"such":[34,77,101,196],"corpora":[35],"usually":[36],"comply":[37],"with":[38,82],"standard":[39,83],"linguistic,":[40],"spelling":[41],"and":[42,74,156,172],"typographic":[43],"conventions.":[44],"meantime,":[47],"emergence":[49],"of":[50,59,62,71,129,193],"Web":[51,137],"2.0":[52,138],"communication":[53],"media":[54],"has":[55],"caused":[56],"apparition":[58],"new":[60],"types":[61],"online":[63],"textual":[64],"data.":[65,102],"Although":[66],"valuable,":[67],"e.g.,":[68],"in":[69,199],"terms":[70],"mining":[73],"sentiment":[75],"analysis,":[76],"user-generated":[78,116],"content":[79,117],"rarely":[80],"complies":[81],"conventions:":[84],"they":[85],"noisy.":[87],"This":[88,188],"prevents":[89],"NLP":[91],"tools,":[92],"especially":[93],"treebank":[94,118,155],"based":[95],"parsers,":[96],"performing":[98],"well":[99],"For":[103],"this":[104,130,154],"reason,":[105],"we":[106,152,160],"developed":[108],"French":[110],"Social":[111],"Media":[112],"Bank,":[113],"first":[115,127],"for":[119,144,162],"French,":[120],"a":[121,200],"morphologically":[122],"rich":[123],"language":[124],"(MRL).":[125],"The":[126],"release":[128],"resource":[131],"contains":[132],"1,700":[133],"sentences":[134],"various":[136],"sources,":[139],"including":[140],"specifically":[142],"chosen":[143],"their":[145],"noisiness.":[147],"We":[148,166],"describe":[149],"here":[150],"how":[151],"created":[153],"expose":[157],"methodology":[159],"used":[161],"fully":[163],"annotating":[164],"it.":[165],"also":[167],"provide":[168],"baseline":[169],"POS":[170],"tagging":[171],"constituency":[174],"results,":[176],"which":[177],"lower":[179],"by":[180],"far":[181],"than":[182],"usual":[183],"edited":[186],"highlights":[189],"difficulty":[192],"automatically":[194],"processing":[195],"noisy":[197],"MRL.":[201]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}