{"id":"https://openalex.org/W2107928532","doi":"https://doi.org/10.1162/089120105774321073","title":"Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II and Penn-III Treebanks","display_name":"Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II and Penn-III Treebanks","publication_year":2005,"publication_date":"2005-09-01","ids":{"openalex":"https://openalex.org/W2107928532","doi":"https://doi.org/10.1162/089120105774321073","mag":"2107928532"},"language":"en","primary_location":{"id":"doi:10.1162/089120105774321073","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105774321073","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105774321073","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":"hybrid","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105774321073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057142942","display_name":"Ruth O'Donovan","orcid":null},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Ruth O'Donovan","raw_affiliation_strings":["Dublin City University","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059032849","display_name":"Michael Burke","orcid":"https://orcid.org/0000-0001-7426-1498"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Michael Burke","raw_affiliation_strings":["Dublin City University","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048408884","display_name":"Aoife Cahill","orcid":null},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Aoife Cahill","raw_affiliation_strings":["Dublin City University","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049194403","display_name":"Josef van Genabith","orcid":"https://orcid.org/0000-0003-1322-7944"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Josef van Genabith","raw_affiliation_strings":["Dublin City University","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055864641","display_name":"Andy Way","orcid":"https://orcid.org/0000-0001-5736-5930"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Andy Way","raw_affiliation_strings":["Dublin City University","Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057142942"],"corresponding_institution_ids":["https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":4.5943,"has_fulltext":true,"cited_by_count":76,"citation_normalized_percentile":{"value":0.945875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"31","issue":"3","first_page":"329","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T13629","display_name":"Text Readability and Simplification","score":0.9825999736785889,"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/subcategorization","display_name":"Subcategorization","score":0.9528059363365173},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.742289662361145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7342054843902588},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6687138080596924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6685646176338196},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.667438805103302},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.5817043781280518},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5493747591972351},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42592793703079224},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.42478829622268677},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41364091634750366},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3058963418006897},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11758953332901001}],"concepts":[{"id":"https://openalex.org/C70845037","wikidata":"https://www.wikidata.org/wiki/Q6980760","display_name":"Subcategorization","level":3,"score":0.9528059363365173},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.742289662361145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342054843902588},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6687138080596924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6685646176338196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.667438805103302},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.5817043781280518},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5493747591972351},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42592793703079224},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42478829622268677},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41364091634750366},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3058963418006897},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11758953332901001},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/089120105774321073","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105774321073","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105774321073","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doras.dcu.ie:16178","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401511","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:http://www.rian.ie/48265/","is_oa":true,"landing_page_url":"http://doras.dcu.ie/16178/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"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":"O'Donovan, Ruth, Burke, Michael, Cahill, Aoife ORCID: 0000-0002-3519-7726 &lt;https://orcid.org/0000-0002-3519-7726&gt;, van Genabith, Josef and Way, Andy ORCID: 0000-0001-5736-5930 &lt;https://orcid.org/0000-0001-5736-5930&gt;  (2005) Large-scale induction and evaluation of lexical resources from the Penn-II and Penn-III treebanks.  Computational Linguistics, 31  (3).   pp. 328-365.  ISSN 1530-9312","raw_type":"Other"},{"id":"pmh:oai:doaj.org/article:177c5080f1394fbfbfb97e409d4174a6","is_oa":false,"landing_page_url":"https://doaj.org/article/177c5080f1394fbfbfb97e409d4174a6","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 31, Iss 3 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120105774321073","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105774321073","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105774321073","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320834","display_name":"Enterprise Ireland","ror":"https://ror.org/023z51242"},{"id":"https://openalex.org/F4320320842","display_name":"Irish Research Council for Science, Engineering and Technology","ror":"https://ror.org/051xex213"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2107928532.pdf","grobid_xml":"https://content.openalex.org/works/W2107928532.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W12836875","https://openalex.org/W13173216","https://openalex.org/W35730636","https://openalex.org/W51017284","https://openalex.org/W51915464","https://openalex.org/W101026854","https://openalex.org/W139296928","https://openalex.org/W295202501","https://openalex.org/W1479758177","https://openalex.org/W1491161564","https://openalex.org/W1521190430","https://openalex.org/W1550242138","https://openalex.org/W1554616486","https://openalex.org/W1574661744","https://openalex.org/W1622422412","https://openalex.org/W1722351164","https://openalex.org/W1859173823","https://openalex.org/W1924403233","https://openalex.org/W1957922405","https://openalex.org/W1967689119","https://openalex.org/W1968680380","https://openalex.org/W1980317580","https://openalex.org/W1986543644","https://openalex.org/W1991923024","https://openalex.org/W2008172256","https://openalex.org/W2028637605","https://openalex.org/W2038248725","https://openalex.org/W2088198454","https://openalex.org/W2093647425","https://openalex.org/W2096945176","https://openalex.org/W2107126982","https://openalex.org/W2110529160","https://openalex.org/W2112589528","https://openalex.org/W2118785474","https://openalex.org/W2122978558","https://openalex.org/W2123325748","https://openalex.org/W2134436204","https://openalex.org/W2142639918","https://openalex.org/W2153439141","https://openalex.org/W2156141032","https://openalex.org/W2156367800","https://openalex.org/W2161204834","https://openalex.org/W2161349060","https://openalex.org/W2268733724","https://openalex.org/W2425667873","https://openalex.org/W2597531846","https://openalex.org/W3037557769","https://openalex.org/W4205167092","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4250844750","https://openalex.org/W2136028896","https://openalex.org/W2914364344","https://openalex.org/W1849825599","https://openalex.org/W4232741964","https://openalex.org/W2027556791","https://openalex.org/W2343959371","https://openalex.org/W1596786534","https://openalex.org/W2353758311","https://openalex.org/W2204098871"],"abstract_inverted_index":{"We":[0,24,138],"present":[1,139],"a":[2,123,140],"methodology":[3],"for":[4,18,49,54,118,171],"extracting":[5],"subcategorization":[6,27,36,97,167],"frames":[7,28,37,62,168],"based":[8],"on":[9,64],"an":[10,130],"automatic":[11],"lexical-functional":[12],"grammar":[13],"(LFG)":[14],"f-structure":[15],"annotation":[16],"algorithm":[17],"the":[19,65,76,82,96,105,144,151,160],"Penn-II":[20],"and":[21,32,51,70,73,110,129,162],"Penn-III":[22],"Treebanks.":[23],"extract":[25,113],"syntactic-function-based":[26],"(LFG":[29],"semantic":[30],"forms)":[31],"traditional":[33],"CFG":[34],"category-based":[35],"as":[38,40],"well":[39],"mixed":[41],"function/category-based":[42],"frames,":[43,72],"with":[44,61,122],"or":[45],"without":[46],"preposition":[47],"information":[48,53],"obliques":[50],"particle":[52,55],"verbs.":[56],"Our":[57],"approach":[58],"associates":[59],"probabilities":[60],"conditional":[63],"lemma,":[66],"distinguishes":[67],"between":[68],"active":[69],"passive":[71],"fully":[74],"reflects":[75],"effects":[77],"of":[78,125,132,143,147,166],"long-distance":[79],"dependencies":[80],"in":[81],"source":[83,106],"data":[84],"structures.":[85],"In":[86],"contrast":[87],"to":[88],"many":[89],"other":[90],"approaches,":[91],"ours":[92],"does":[93],"not":[94],"predefine":[95],"frame":[98,116,127,134],"types":[99,117,128,135],"extracted,":[100],"learning":[101],"them":[102],"instead":[103],"from":[104],"data.":[107],"Including":[108],"particles":[109],"prepositions,":[111],"we":[112],"21,005":[114],"lemma":[115],"4,362":[119],"verb":[120],"lemmas,":[121],"total":[124],"577":[126],"average":[131],"4.8":[133],"per":[136],"verb.":[137],"large-scale":[141],"evaluation":[142,165],"complete":[145,164],"set":[146],"forms":[148],"extracted":[149],"against":[150],"full":[152],"COMLEX":[153],"resource.":[154],"To":[155],"our":[156],"knowledge,":[157],"this":[158],"is":[159],"largest":[161],"most":[163],"acquired":[169],"automatically":[170],"English.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":35}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
