{"id":"https://openalex.org/W2741200141","doi":"https://doi.org/10.18653/v1/w17-1702","title":"Multi-word Entity Classification in a Highly Multilingual Environment","display_name":"Multi-word Entity Classification in a Highly Multilingual Environment","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2741200141","doi":"https://doi.org/10.18653/v1/w17-1702","mag":"2741200141"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-1702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1702","pdf_url":"https://www.aclweb.org/anthology/W17-1702.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 13th Workshop on Multiword Expressions (MWE 2017)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-1702.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089543759","display_name":"Sophie Chesney","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["GB","IT"],"is_corresponding":true,"raw_author_name":"Sophie Chesney","raw_affiliation_strings":["Cognitive Science Research Group, School of Electronic Engineering and Computer Science, Queen Mary University of London, UK","Text and Data Mining Unit, Joint Research Centre, European Commission, Ispra, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Science Research Group, School of Electronic Engineering and Computer Science, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Text and Data Mining Unit, Joint Research Centre, European Commission, Ispra, Italy","institution_ids":["https://openalex.org/I4210118689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091828530","display_name":"Guillaume Jacquet","orcid":"https://orcid.org/0000-0001-8388-3897"},"institutions":[{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Guillaume Jacquet","raw_affiliation_strings":["Text and Data Mining Unit, Joint Research Centre, European Commission, Ispra, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Text and Data Mining Unit, Joint Research Centre, European Commission, Ispra, Italy","institution_ids":["https://openalex.org/I4210118689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109895385","display_name":"Ralf Steinberger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ralf Steinberger","raw_affiliation_strings":["Text and Data Mining Unit, Joint Research Centre, European Commission, Ispra, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Text and Data Mining Unit, Joint Research Centre, European Commission, Ispra, Italy","institution_ids":["https://openalex.org/I4210118689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090741889","display_name":"Jakub Piskorski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Jakub Piskorski","raw_affiliation_strings":["Text and Data Mining Unit, Joint Research Centre, European Commission, Ispra, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Text and Data Mining Unit, Joint Research Centre, European Commission, Ispra, Italy","institution_ids":["https://openalex.org/I4210118689"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089543759"],"corresponding_institution_ids":["https://openalex.org/I166337079","https://openalex.org/I4210118689"],"apc_list":null,"apc_paid":null,"fwci":1.1074,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82771716,"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":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9979000091552734,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.8300772905349731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7551364898681641},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7354611158370972},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6430578827857971},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5977454781532288},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5427983999252319},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49898838996887207},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.49555742740631104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34050941467285156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06831023097038269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300772905349731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7551364898681641},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7354611158370972},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6430578827857971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5977454781532288},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5427983999252319},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49898838996887207},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.49555742740631104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34050941467285156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06831023097038269},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w17-1702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1702","pdf_url":"https://www.aclweb.org/anthology/W17-1702.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 13th Workshop on Multiword Expressions (MWE 2017)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.jrc.ec.europa.eu:111111111/50452","is_oa":true,"landing_page_url":"http://aclweb.org/anthology/W17-17","pdf_url":null,"source":{"id":"https://openalex.org/S4306401126","display_name":"Joint Research Centre (European Commission)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800387288","host_organization_name":"European Commission","host_organization_lineage":["https://openalex.org/I2800387288"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Articles in periodicals and books"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-1702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1702","pdf_url":"https://www.aclweb.org/anthology/W17-1702.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 13th Workshop on Multiword Expressions (MWE 2017)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311061","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334701","display_name":"Joint Research Centre","ror":"https://ror.org/04j5wtv36"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741200141.pdf","grobid_xml":"https://content.openalex.org/works/W2741200141.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W166868646","https://openalex.org/W167355512","https://openalex.org/W178774507","https://openalex.org/W2005422315","https://openalex.org/W2010450719","https://openalex.org/W2038721957","https://openalex.org/W2094728533","https://openalex.org/W2101234009","https://openalex.org/W2120699290","https://openalex.org/W2120844411","https://openalex.org/W2141035425","https://openalex.org/W2149684865","https://openalex.org/W2151846280","https://openalex.org/W2168505588","https://openalex.org/W2172000360","https://openalex.org/W2251239360","https://openalex.org/W2293004735","https://openalex.org/W2406945108","https://openalex.org/W2470203008","https://openalex.org/W3123097419"],"related_works":["https://openalex.org/W2357114597","https://openalex.org/W2115416187","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W202723009","https://openalex.org/W1999699871","https://openalex.org/W4225124612"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,45,99],"approach":[4],"for":[5,95],"the":[6,28,70,109,122,127,131],"classification":[7],"of":[8,10,41,48,86,102,118],"millions":[9],"existing":[11],"multiword":[12],"entities":[13],"(MWEntities),":[14],"such":[15],"as":[16],"organisation":[17],"or":[18],"event":[19],"names,":[20],"into":[21,44],"thirteen":[22],"category":[23],"types,":[24],"based":[25,60],"only":[26],"on":[27,61,83],"tokens":[29],"they":[30],"contain.":[31],"In":[32,104],"order":[33],"to":[34,125],"classify":[35],"our":[36],"very":[37],"large":[38],"in-house":[39],"collection":[40],"multilingual":[42],"MWEntities":[43,62],"application-oriented":[46],"set":[47],"entity":[49],"categories,":[50],"we":[51,107],"trained":[52,82,94],"and":[53,111,129],"tested":[54],"distantly-supervised":[55],"classifiers":[56,93],"in":[57],"43":[58],"languages":[59,88],"extracted":[63],"from":[64],"BabelNet.":[65],"The":[66],"best-performing":[67],"classifier":[68,81],"was":[69],"multi-class":[71],"SVM":[72],"using":[73],"a":[74,84,115],"TF.IDF-weighted":[75],"data":[76],"representation.":[77],"Interestingly,":[78],"one":[79],"unique":[80],"mix":[85],"all":[87],"consistently":[89],"performed":[90],"better":[91],"than":[92],"individual":[96],"languages,":[97],"reaching":[98],"averaged":[100],"F1-value":[101],"88.8%.":[103],"this":[105],"paper,":[106],"present":[108],"training":[110],"test":[112],"data,":[113],"including":[114],"human":[116],"evaluation":[117],"its":[119],"accuracy,":[120],"describe":[121],"methods":[123],"used":[124],"train":[126],"classifiers,":[128],"discuss":[130],"results.":[132]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}