{"id":"https://openalex.org/W2007119365","doi":"https://doi.org/10.3115/1075218.1075229","title":"Tagging unknown proper names using decision trees","display_name":"Tagging unknown proper names using decision trees","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2007119365","doi":"https://doi.org/10.3115/1075218.1075229","mag":"2007119365"},"language":"en","primary_location":{"id":"doi:10.3115/1075218.1075229","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075229","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075218.1075229","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics - ACL '00","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1075218.1075229","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110498175","display_name":"Fr\u00e9d\u00e9ric B\u00e9chet","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]},{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric B\u00e9chet","raw_affiliation_strings":["LIA Universit\u00e9 d'Avignon","LIA, Universit\u00e9 d\u2019Avignon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA Universit\u00e9 d'Avignon","institution_ids":["https://openalex.org/I4210119991"]},{"raw_affiliation_string":"LIA, Universit\u00e9 d\u2019Avignon","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028541034","display_name":"Alexis Nasr","orcid":"https://orcid.org/0000-0001-7573-3282"},"institutions":[{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexis Nasr","raw_affiliation_strings":["LIM Universit\u00e9 Aix-Marseille","LIM Universit\u00e9 Aix-Marseille#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIM Universit\u00e9 Aix-Marseille","institution_ids":["https://openalex.org/I21491767"]},{"raw_affiliation_string":"LIM Universit\u00e9 Aix-Marseille#TAB#","institution_ids":["https://openalex.org/I21491767"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047718471","display_name":"Franck Genet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franck Genet","raw_affiliation_strings":["Fr\u00e9d\u00e9ric B\u00e9chet","Fr\u00e9d\u00e9ric B\u00e9chet#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fr\u00e9d\u00e9ric B\u00e9chet","institution_ids":[]},{"raw_affiliation_string":"Fr\u00e9d\u00e9ric B\u00e9chet#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.9872999787330627,"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":0.7730559706687927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7090039849281311},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6481497287750244},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5629357099533081},{"id":"https://openalex.org/keywords/proper-noun","display_name":"Proper noun","score":0.5583438873291016},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5218157172203064},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5066514611244202},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4647231698036194},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.44265884160995483},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.44238147139549255},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41267484426498413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35814937949180603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17334327101707458},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1277792751789093},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06715577840805054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730559706687927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7090039849281311},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6481497287750244},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5629357099533081},{"id":"https://openalex.org/C41417386","wikidata":"https://www.wikidata.org/wiki/Q147276","display_name":"Proper noun","level":2,"score":0.5583438873291016},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5218157172203064},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5066514611244202},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4647231698036194},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.44265884160995483},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.44238147139549255},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41267484426498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35814937949180603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17334327101707458},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1277792751789093},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06715577840805054},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1075218.1075229","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075229","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075218.1075229","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics - ACL '00","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.3606","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.3606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lif-sud.univ-mrs.fr/~nasr/Rech/Publi/acl00.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.7986","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.7986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P00/P00-1011.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1075218.1075229","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075229","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075218.1075229","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics - ACL '00","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2007119365.pdf","grobid_xml":"https://content.openalex.org/works/W2007119365.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1520377376","https://openalex.org/W1552860512","https://openalex.org/W1594031697","https://openalex.org/W1718065290","https://openalex.org/W2029433174","https://openalex.org/W2123379364","https://openalex.org/W2166394306","https://openalex.org/W2785349534","https://openalex.org/W3085162807","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3118607722","https://openalex.org/W2803492476","https://openalex.org/W924436176","https://openalex.org/W1524602228","https://openalex.org/W2025590371","https://openalex.org/W4206326973","https://openalex.org/W2919547998","https://openalex.org/W2943690567","https://openalex.org/W2549028007","https://openalex.org/W1979321383"],"abstract_inverted_index":{"This":[0,51,70],"paper":[1],"describes":[2],"a":[3,11,34,68,81],"supervised":[4],"learning":[5,31],"method":[6],"to":[7,55,76],"automatically":[8],"select":[9],"from":[10],"set":[12],"of":[13,19,29,46,49,60,63,80,84],"noun":[14],"phrases,":[15],"embedding":[16],"proper":[17,41,65],"names":[18],"different":[20],"semantic":[21],"classes,":[22],"their":[23],"most":[24],"distinctive":[25],"features.":[26],"The":[27],"result":[28],"the":[30,44,57,78],"process":[32],"is":[33,53,73],"decision":[35],"tree":[36],"which":[37],"classifies":[38],"an":[39,61],"unknown":[40],"name":[42,66],"on":[43],"basis":[45],"its":[47],"context":[48],"occurrence.":[50],"classifier":[52],"used":[54,75],"estimate":[56,77],"probability":[58,71],"distribution":[59,72],"out":[62],"vocabulary":[64],"over":[67],"tagset.":[69],"itself":[74],"parameters":[79],"stochastic":[82],"part":[83],"speech":[85],"tagger.":[86]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}