{"id":"https://openalex.org/W1971579776","doi":"https://doi.org/10.1162/coli_a_00149","title":"Text Representations for Patent Classification","display_name":"Text Representations for Patent Classification","publication_year":2012,"publication_date":"2012-11-16","ids":{"openalex":"https://openalex.org/W1971579776","doi":"https://doi.org/10.1162/coli_a_00149","mag":"1971579776"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00149","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00149","pdf_url":"https://direct.mit.edu/coli/article-pdf/39/3/755/1801916/coli_a_00149.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/coli/article-pdf/39/3/755/1801916/coli_a_00149.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084625140","display_name":"Eva D\u2019Hondt","orcid":"https://orcid.org/0000-0001-5646-2261"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Eva D'hondt","raw_affiliation_strings":["Radboud University Nijmegen","Radboud University Nijmegen#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University Nijmegen#TAB#","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027124439","display_name":"Suzan Verberne","orcid":"https://orcid.org/0000-0002-9609-9505"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Suzan Verberne","raw_affiliation_strings":["Radboud University Nijmegen","Radboud University Nijmegen#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University Nijmegen#TAB#","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032872149","display_name":"C. H. A. Koster","orcid":"https://orcid.org/0009-0000-3393-6110"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cornelis Koster","raw_affiliation_strings":["Radboud University Nijmegen","Radboud University Nijmegen#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University Nijmegen#TAB#","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037500994","display_name":"Lou Boves","orcid":"https://orcid.org/0000-0002-1942-9355"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lou Boves","raw_affiliation_strings":["Radboud University Nijmegen","Radboud University Nijmegen#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University Nijmegen#TAB#","institution_ids":["https://openalex.org/I145872427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084625140"],"corresponding_institution_ids":["https://openalex.org/I145872427"],"apc_list":null,"apc_paid":null,"fwci":2.0155,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.85934257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"39","issue":"3","first_page":"755","last_page":"775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9897000193595886,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9876999855041504,"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/bigram","display_name":"Bigram","score":0.9784688949584961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8200303316116333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7207177877426147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6678482294082642},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5621734261512756},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5150330066680908},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4503836929798126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36421048641204834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07708346843719482}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9784688949584961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200303316116333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7207177877426147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6678482294082642},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5621734261512756},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5150330066680908},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4503836929798126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36421048641204834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07708346843719482},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/coli_a_00149","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00149","pdf_url":"https://direct.mit.edu/coli/article-pdf/39/3/755/1801916/coli_a_00149.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:40571328397c467bb7ee0783517b97dd","is_oa":false,"landing_page_url":"https://doaj.org/article/40571328397c467bb7ee0783517b97dd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 39, Iss 3 (2021)","raw_type":"article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/111266","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/111266","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article / Letter to editor"},{"id":"pmh:ru:oai:repository.ubn.ru.nl:2066/111266","is_oa":true,"landing_page_url":"http://hdl.handle.net/2066/111266","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Computational Linguistics, 39, 755 - 775","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00149","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00149","pdf_url":"https://direct.mit.edu/coli/article-pdf/39/3/755/1801916/coli_a_00149.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1971579776.pdf","grobid_xml":"https://content.openalex.org/works/W1971579776.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W27438036","https://openalex.org/W69295931","https://openalex.org/W79183852","https://openalex.org/W165033579","https://openalex.org/W187991193","https://openalex.org/W1487232999","https://openalex.org/W1497812196","https://openalex.org/W1522930027","https://openalex.org/W1523389133","https://openalex.org/W1524281572","https://openalex.org/W1569385487","https://openalex.org/W1574862351","https://openalex.org/W1576676390","https://openalex.org/W1813610639","https://openalex.org/W1941537533","https://openalex.org/W1978394996","https://openalex.org/W2007395264","https://openalex.org/W2027875450","https://openalex.org/W2043558868","https://openalex.org/W2046742505","https://openalex.org/W2075357430","https://openalex.org/W2084319893","https://openalex.org/W2090867003","https://openalex.org/W2092549288","https://openalex.org/W2093098531","https://openalex.org/W2093756022","https://openalex.org/W2094061585","https://openalex.org/W2094934653","https://openalex.org/W2103206127","https://openalex.org/W2104479188","https://openalex.org/W2126502509","https://openalex.org/W2131938067","https://openalex.org/W2134543573","https://openalex.org/W2136454756","https://openalex.org/W2143785854","https://openalex.org/W2170654002","https://openalex.org/W2293771131","https://openalex.org/W2403193557","https://openalex.org/W2528685186","https://openalex.org/W2612085100","https://openalex.org/W4206584443","https://openalex.org/W4285719527","https://openalex.org/W4312960235"],"related_works":["https://openalex.org/W3173084154","https://openalex.org/W2982021180","https://openalex.org/W2251497876","https://openalex.org/W2241081188","https://openalex.org/W2128567707","https://openalex.org/W159278796","https://openalex.org/W2011383762","https://openalex.org/W2035962958","https://openalex.org/W2360858150","https://openalex.org/W370365947"],"abstract_inverted_index":{"With":[0],"the":[1,30,34,41,48,61,74,88,95,104,118,133,141,144,183],"increasing":[2],"rate":[3],"of":[4,12,29,43,50,69,97,132,151,176,185],"patent":[5,9,20,31,93,157],"application":[6],"filings,":[7],"automated":[8],"classification":[10,21,84,94,168],"is":[11],"rising":[13],"economic":[14],"importance.":[15],"This":[16,127],"article":[17,128],"investigates":[18],"how":[19],"can":[22],"be":[23],"improved":[24],"by":[25,112,121,140],"using":[26],"different":[27,57],"representations":[28],"documents.":[32],"Using":[33],"Linguistic":[35],"Classification":[36],"System":[37],"(LCS),":[38],"we":[39],"compare":[40],"impact":[42],"adding":[44],"statistical":[45],"phrases":[46,54,86,98,152],"(in":[47,55],"form":[49],"bigrams)":[51],"and":[52,117,124,178],"linguistic":[53],"two":[56],"dependency":[58],"formats)":[59],"to":[60,80,147,165,181],"standard":[62],"bag-of-words":[63],"text":[64],"representation":[65],"on":[66,83,174],"a":[67],"subset":[68],"532,264":[70],"English":[71],"abstracts":[72,180],"from":[73],"CLEF-IP":[75],"2010":[76],"corpus.":[77],"In":[78],"contrast":[79],"previous":[81],"findings":[82],"with":[85],"in":[87,100,143,167],"Reuters-21578":[89],"data":[90],"set,":[91],"for":[92,156],"addition":[96],"results":[99,109],"significant":[101],"improvements":[102,166],"over":[103],"unigram":[105],"baseline.":[106],"The":[107],"best":[108,120],"were":[110,172],"achieved":[111],"combining":[113,122],"all":[114],"four":[115],"representations,":[116],"second":[119],"unigrams":[123],"lemmatized":[125],"bigrams.":[126],"includes":[129],"extensive":[130],"analyses":[131],"class":[134,137],"models":[135],"(a.k.a.":[136],"profiles)":[138],"created":[139],"classifiers":[142],"LCS":[145],"framework,":[146],"examine":[148],"which":[149],"types":[150],"are":[153],"most":[154,164],"informative":[155],"classification.":[158],"It":[159],"appears":[160],"that":[161],"bigrams":[162],"contribute":[163],"accuracy.":[169],"Similar":[170],"experiments":[171],"performed":[173],"subsets":[175],"French":[177],"German":[179],"investigate":[182],"generalizability":[184],"these":[186],"findings.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
