{"id":"https://openalex.org/W2078244995","doi":"https://doi.org/10.1162/coli_a_00076","title":"Parsing Noun Phrases in the Penn Treebank","display_name":"Parsing Noun Phrases in the Penn Treebank","publication_year":2011,"publication_date":"2011-07-14","ids":{"openalex":"https://openalex.org/W2078244995","doi":"https://doi.org/10.1162/coli_a_00076","mag":"2078244995"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00076","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00076","pdf_url":"https://direct.mit.edu/coli/article-pdf/37/4/753/1798909/coli_a_00076.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/37/4/753/1798909/coli_a_00076.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061948215","display_name":"David Vadas","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Vadas","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024711700","display_name":"James Curran","orcid":"https://orcid.org/0000-0001-9637-0484"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"James R. Curran","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":1.8293,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88394224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"37","issue":"4","first_page":"753","last_page":"809"},"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":0.9994999766349792,"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/T13629","display_name":"Text Readability and Simplification","score":0.9929999709129333,"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/treebank","display_name":"Treebank","score":0.9444897174835205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8844065070152283},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8098632097244263},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7858411073684692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7477050423622131},{"id":"https://openalex.org/keywords/bracketing","display_name":"Bracketing (phenomenology)","score":0.7062205076217651},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5718328952789307},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.48733314871788025},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4804929494857788},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.4620627164840698},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.43382734060287476},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.412738174200058},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10497042536735535}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9444897174835205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8844065070152283},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8098632097244263},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7858411073684692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7477050423622131},{"id":"https://openalex.org/C102944935","wikidata":"https://www.wikidata.org/wiki/Q4953701","display_name":"Bracketing (phenomenology)","level":2,"score":0.7062205076217651},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5718328952789307},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.48733314871788025},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4804929494857788},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.4620627164840698},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.43382734060287476},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.412738174200058},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10497042536735535},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_a_00076","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00076","pdf_url":"https://direct.mit.edu/coli/article-pdf/37/4/753/1798909/coli_a_00076.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:CiteSeerX.psu:10.1.1.222.2570","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.222.2570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology-new/J/J11/J11-4006.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:f46033bdfaac475eb4a13404100d530d","is_oa":false,"landing_page_url":"https://doaj.org/article/f46033bdfaac475eb4a13404100d530d","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 37, Iss 4 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00076","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00076","pdf_url":"https://direct.mit.edu/coli/article-pdf/37/4/753/1798909/coli_a_00076.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2078244995.pdf","grobid_xml":"https://content.openalex.org/works/W2078244995.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W54534146","https://openalex.org/W76590478","https://openalex.org/W195275552","https://openalex.org/W1499580382","https://openalex.org/W1502293651","https://openalex.org/W1507020546","https://openalex.org/W1525632714","https://openalex.org/W1535015163","https://openalex.org/W1551104980","https://openalex.org/W1567277581","https://openalex.org/W1567570606","https://openalex.org/W1585743408","https://openalex.org/W1623072288","https://openalex.org/W1632114991","https://openalex.org/W1809152426","https://openalex.org/W1859173823","https://openalex.org/W1924403233","https://openalex.org/W1964388487","https://openalex.org/W1965745145","https://openalex.org/W1970961429","https://openalex.org/W1981724541","https://openalex.org/W1986543644","https://openalex.org/W2038721957","https://openalex.org/W2043814069","https://openalex.org/W2062837929","https://openalex.org/W2067349145","https://openalex.org/W2075790020","https://openalex.org/W2079326125","https://openalex.org/W2085575316","https://openalex.org/W2087099129","https://openalex.org/W2087165009","https://openalex.org/W2092654472","https://openalex.org/W2093647425","https://openalex.org/W2100448020","https://openalex.org/W2101105183","https://openalex.org/W2102967855","https://openalex.org/W2110882317","https://openalex.org/W2115321439","https://openalex.org/W2116159459","https://openalex.org/W2117424365","https://openalex.org/W2121407024","https://openalex.org/W2138607469","https://openalex.org/W2139117344","https://openalex.org/W2139621418","https://openalex.org/W2143458716","https://openalex.org/W2144778997","https://openalex.org/W2152907450","https://openalex.org/W2153439141","https://openalex.org/W2155759494","https://openalex.org/W2159705183","https://openalex.org/W2165405828","https://openalex.org/W2171332413","https://openalex.org/W2305592425","https://openalex.org/W2334801970","https://openalex.org/W2796493717","https://openalex.org/W2963847008","https://openalex.org/W2989631226","https://openalex.org/W3041733660","https://openalex.org/W4241850027","https://openalex.org/W4392051461"],"related_works":["https://openalex.org/W1534334044","https://openalex.org/W2019068568","https://openalex.org/W2229162816","https://openalex.org/W2044122727","https://openalex.org/W1507020546","https://openalex.org/W2072743731","https://openalex.org/W2756798860","https://openalex.org/W3011924861","https://openalex.org/W2250416224","https://openalex.org/W199416282"],"abstract_inverted_index":{"Noun":[0],"phrases":[1],"(nps)":[2],"are":[3,251],"a":[4,13,166,184,195,219,271,288,307],"crucial":[5],"part":[6],"of":[7,42,90,147,186,210,291,321,334],"natural":[8],"language,":[9],"and":[10,110,142,242,305,324],"can":[11,330],"have":[12,61],"very":[14],"complex":[15,248],"structure.":[16,336],"However,":[17],"this":[18,76,133,178,191,263],"np":[19,81,114,120,148,198,284,335],"structure":[20,82,149],"is":[21,35,107,116,122,150,160,180,208],"largely":[22],"ignored":[23],"by":[24,78,183,278,314],"the":[25,30,57,84,91,102,105,137,233,256,279,295,302,311,319,322],"statistical":[26],"parsing":[27,140],"field,":[28],"as":[29,306],"most":[31,237],"widely":[32],"used":[33,215],"corpus":[34],"not":[36],"annotated":[37],"with":[38,132,254],"it.":[39],"This":[40],"lack":[41,185],"gold-standard":[43,119],"data":[44,121,205],"has":[45,240],"restricted":[46],"previous":[47,238],"efforts":[48],"to":[49,55,162,244],"parse":[50],"nps,":[51],"making":[52],"it":[53],"impossible":[54],"perform":[56],"supervised":[58,220],"experiments":[59,317],"that":[60,98,104,112,144,168,177,222,236,250,274,293,298,326],"achieved":[62],"high":[63],"performance":[64],"in":[65,127,255],"so":[66],"many":[67,327],"Natural":[68],"Language":[69],"Processing":[70],"(nlp)":[71],"tasks.":[72],"We":[73,130,258],"comprehensively":[74],"solve":[75,190],"problem":[77,192],"manually":[79],"annotating":[80],"for":[83,125],"entire":[85],"Wall":[86],"Street":[87],"Journal":[88],"section":[89],"Penn":[92,203],"Treebank.":[93],"The":[94,157],"inter-annotator":[95],"agreement":[96],"scores":[97],"we":[99,175,193,217,269,309],"attain":[100,259],"dispel":[101],"belief":[103],"task":[106,235],"too":[108],"difficult,":[109],"demonstrate":[111,318],"consistent":[113],"annotation":[115],"possible.":[117],"Our":[118,226,283],"now":[123,331],"available":[124],"use":[126,333],"all":[128],"parsers.":[129],"experiment":[131],"new":[134],"data,":[135],"applying":[136],"Collins":[138],"(2003)":[139],"model,":[141],"find":[143],"its":[145,154],"recovery":[146],"significantly":[151],"worse":[152],"than":[153,165,213],"overall":[155],"performance.":[156],"parser's":[158,312],"F-score":[159,231,261,313],"up":[161],"5.69%":[163],"lower":[164],"baseline":[167],"uses":[169],"deterministic":[170],"rules.":[171],"Through":[172],"much":[173,264],"experimentation,":[174],"determine":[176],"result":[179],"primarily":[181],"caused":[182],"lexical":[187,296],"information.":[188],"To":[189],"construct":[194],"wide-coverage,":[196],"large-scale":[197],"Bracketing":[199,285],"system.":[200],"With":[201],"our":[202],"Treebank":[204],"set,":[206],"which":[207],"orders":[209],"magnitude":[211],"larger":[212],"those":[214],"previously,":[216],"build":[218],"model":[221,227,286],"achieves":[223],"excellent":[224],"results.":[225],"performs":[228],"at":[229],"93.8%":[230],"on":[232,262],"simple":[234],"work":[239],"undertaken,":[241],"extends":[243],"bracket":[245],"longer,":[246],"more":[247,265],"nps":[249,276],"rarely":[252],"dealt":[253],"literature.":[257],"89.14%":[260],"difficult":[266],"task.":[267],"Finally,":[268],"implement":[270],"post-processing":[272],"module":[273],"brackets":[275],"identified":[277],"Bikel":[280],"(2004)":[281],"parser.":[282],"includes":[287],"wide":[289],"variety":[290],"features":[292],"provide":[294],"information":[297],"was":[299],"missing":[300],"during":[301],"parser":[303],"experiments,":[304],"result,":[308],"outperform":[310],"9.04%.":[315],"These":[316],"utility":[320],"corpus,":[323],"show":[325],"nlp":[328],"applications":[329],"make":[332]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}