{"id":"https://openalex.org/W2209845672","doi":null,"title":"Building a treebank of noisy user-generated content: The French Social Media Bank","display_name":"Building a treebank of noisy user-generated content: The French Social Media Bank","publication_year":2012,"publication_date":"2012-11-30","ids":{"openalex":"https://openalex.org/W2209845672","mag":"2209845672"},"language":"fr","primary_location":{"id":"pmh:oai:HAL:hal-00780898v1","doi":null,"is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00780898","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://pauillac.inria.fr/~seddah/tlt2012.pdf","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","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/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":["Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing","Universit\u00e9 Paris-Sorbonne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing","institution_ids":["https://openalex.org/I4405261320"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Sorbonne","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/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":["Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing","institution_ids":["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/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":["Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing","institution_ids":["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/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":["Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing","institution_ids":["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/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":["Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse Linguistique Profonde \u00e0 Grande Echelle ; Large-scale deep linguistic processing","institution_ids":["https://openalex.org/I4405261320"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"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":0.9965999722480774,"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":0.9965999722480774,"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":0.0015999999595806003,"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":0.0006000000284984708,"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":0.8009999990463257},{"id":"https://openalex.org/keywords/user-generated-content","display_name":"user-generated content","score":0.9710000157356262},{"id":"https://openalex.org/keywords/social-media","display_name":"social media","score":0.7239999771118164},{"id":"https://openalex.org/keywords/noisy-text","display_name":"noisy text","score":0.5519999861717224},{"id":"https://openalex.org/keywords/french-language","display_name":"French language","score":0.7749999761581421},{"id":"https://openalex.org/keywords/web-2-0","display_name":"Web 2.0","score":0.9039999842643738},{"id":"https://openalex.org/keywords/facebook","display_name":"Facebook","score":0.5490000247955322},{"id":"https://openalex.org/keywords/twitter","display_name":"Twitter","score":0.9950000047683716},{"id":"https://openalex.org/keywords/online-discussion-forums","display_name":"online forums","score":0.8859999775886536},{"id":"https://openalex.org/keywords/sentence-annotation","display_name":"sentence annotation","score":0.3240000009536743}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9853008389472961},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7675428986549377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745509684085846},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.6459271311759949},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4908323884010315},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4672178030014038},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4433358609676361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3629050552845001},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34708529710769653},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3045698404312134},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.08241304755210876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07917141914367676},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-00780898v1","doi":null,"is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00780898","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://pauillac.inria.fr/~seddah/tlt2012.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":12,"referenced_works":["https://openalex.org/W1014376541","https://openalex.org/W1518819622","https://openalex.org/W1518867723","https://openalex.org/W1582588624","https://openalex.org/W1586073462","https://openalex.org/W1865928303","https://openalex.org/W1973346430","https://openalex.org/W2101461018","https://openalex.org/W2134899753","https://openalex.org/W2139621418","https://openalex.org/W2157765050","https://openalex.org/W2533653494"],"related_works":["https://openalex.org/W1014376541","https://openalex.org/W7096211354","https://openalex.org/W4406123353","https://openalex.org/W6981905827","https://openalex.org/W6986997796","https://openalex.org/W7097177370","https://openalex.org/W7099709175","https://openalex.org/W7099693718","https://openalex.org/W7095354056","https://openalex.org/W4393248428"],"abstract_inverted_index":{"We":[0],"introduce":[1],"the":[2,7],"French":[3],"Social":[4],"Media":[5],"Bank,":[6],"first":[8,15],"user-generated":[9],"content":[10],"treebank":[11],"for":[12,36],"French.":[13],"Its":[14],"release":[16],"contains":[17],"1,700":[18],"sentences":[19],"from":[20],"various":[21],"Web":[22],"2.0":[23],"and":[24],"social":[25],"media":[26],"sources":[27],"(FACEBOOK,":[28],"TWITTER,":[29],"web":[30],"forums),":[31],"including":[32],"data":[33],"specifically":[34],"chosen":[35],"their":[37],"high":[38],"noisiness.":[39]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}
