{"id":"https://openalex.org/W121356181","doi":null,"title":"Textual Similarity based on Proper Names","display_name":"Textual Similarity based on Proper Names","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W121356181","mag":"121356181"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.18.5008","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.5008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dcs.vein.hu/CIR/cikkek/friburgerMFIR02.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/A5051176657","display_name":"Nathalie Friburger","orcid":"https://orcid.org/0000-0002-9389-4255","observed_orcids":["https://orcid.org/0000-0002-9389-4255"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathalie Friburger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016470411","display_name":"Denis Maurel","orcid":"https://orcid.org/0000-0002-6752-8243","observed_orcids":["https://orcid.org/0000-0002-6752-8243","https://orcid.org/0000-0001-5658-5923"]},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Denis Maurel","raw_affiliation_strings":["Fran\u00e7ois Rabelais University"],"raw_orcid":"https://orcid.org/0000-0002-6752-8243","affiliations":[{"raw_affiliation_string":"Fran\u00e7ois Rabelais University","institution_ids":["https://openalex.org/I110017253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6942,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.89896038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"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/T10028","display_name":"Topic Modeling","score":0.7689999938011169,"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":0.7689999938011169,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.16130000352859497,"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":0.012900000438094139,"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/proper-names","display_name":"proper names","score":0.9710000157356262},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.9729999899864197},{"id":"https://openalex.org/keywords/text-similarity","display_name":"text similarity","score":0.8489999771118164},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.7139999866485596},{"id":"https://openalex.org/keywords/newspaper-articles","display_name":"newspaper articles","score":0.6349999904632568},{"id":"https://openalex.org/keywords/linguistic-description","display_name":"language description","score":0.5389999747276306},{"id":"https://openalex.org/keywords/automata","display_name":"automata","score":0.8259999752044678},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.8059999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098771929740906},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.6931042671203613},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6709519624710083},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5562049150466919},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5239413380622864},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5171043872833252},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.514751672744751},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4326651692390442},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.43259960412979126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34630247950553894},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3257957696914673},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0878787636756897},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0861588716506958},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.18.5008","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.5008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dcs.vein.hu/CIR/cikkek/friburgerMFIR02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.3531","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.3531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dcs.vein.hu/CIR/cikkek/friburger_MFIR02.pdf","raw_type":"text"},{"id":"mag:121356181","doi":null,"is_oa":false,"landing_page_url":"http://cir.dcs.uni-pannon.hu/cikkek/friburger_MFIR02.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W174154383","https://openalex.org/W1492327544","https://openalex.org/W1521439890","https://openalex.org/W1522930108","https://openalex.org/W1541092193","https://openalex.org/W1658342862","https://openalex.org/W1978394996","https://openalex.org/W1982982698","https://openalex.org/W2035967403","https://openalex.org/W2038827463","https://openalex.org/W2046878543","https://openalex.org/W2056245984","https://openalex.org/W2068632118","https://openalex.org/W2068882115","https://openalex.org/W2145036943","https://openalex.org/W2678478641"],"related_works":["https://openalex.org/W2090236931","https://openalex.org/W116046857","https://openalex.org/W7036537565","https://openalex.org/W2883066278","https://openalex.org/W2956226542","https://openalex.org/W7099313089","https://openalex.org/W2773926527","https://openalex.org/W7011820358","https://openalex.org/W7098725148","https://openalex.org/W1923316804"],"abstract_inverted_index":{"Proper":[0,24],"names":[1,25,59,98],"represent":[2],"about":[3],"10%":[4],"of":[5,83,86,96,101,108],"English":[6],"or":[7],"French":[8],"newspaper":[9,109],"articles.":[10],"Their":[11],"quantity":[12],"and":[13,78],"informational":[14],"quality":[15],"is":[16],"already":[17],"used":[18,61],"in":[19,30,38,62,93,99],"different":[20],"Information":[21,39],"Extraction":[22],"systems.":[23],"have":[26,42],"widely":[27],"been":[28],"studied":[29],"the":[31,84,87,91,94,106],"MUC":[32],"conferences":[33],"designed":[34],"to":[35,69,79,104],"promote":[36],"research":[37],"Extraction.":[40],"We":[41,89],"created":[43],"our":[44],"own":[45],"named":[46],"entity":[47],"extraction":[48],"tool":[49],"based":[50],"on":[51],"a":[52,74,81],"linguistic":[53],"description":[54,82],"with":[55,73],"automata.":[56],"The":[57],"extracted":[58],"are":[60],"an":[63],"information":[64],"retrieval":[65],"process:":[66],"we":[67],"want":[68],"cluster":[70],"journalistic":[71],"texts":[72],"high":[75],"precision":[76],"level":[77],"provide":[80],"topic":[85],"clusters.":[88],"verify":[90],"interest":[92],"use":[95],"proper":[97],"measures":[100],"similarities":[102],"trying":[103],"improve":[105],"clustering":[107],"texts.":[110]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}