{"id":"https://openalex.org/W2092654472","doi":"https://doi.org/10.1162/089120103322753356","title":"Head-Driven Statistical Models for Natural Language Parsing","display_name":"Head-Driven Statistical Models for Natural Language Parsing","publication_year":2003,"publication_date":"2003-12-01","ids":{"openalex":"https://openalex.org/W2092654472","doi":"https://doi.org/10.1162/089120103322753356","mag":"2092654472"},"language":"en","primary_location":{"id":"doi:10.1162/089120103322753356","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322753356","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120103322753356","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":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120103322753356","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079061237","display_name":"Michael Collins","orcid":"https://orcid.org/0000-0003-0997-1527"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Collins","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 545 Technology Square, Cambridge, MA 02139","MIT Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 545 Technology Square, Cambridge, MA 02139. E-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 545 Technology Square, Cambridge, MA 02139","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 545 Technology Square, Cambridge, MA 02139. E-mail:","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079061237"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":208.9357,"has_fulltext":true,"cited_by_count":1860,"citation_normalized_percentile":{"value":0.99997077,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"29","issue":"4","first_page":"589","last_page":"637"},"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":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.994700014591217,"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":0.8670885562896729},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.8610374927520752},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.7364609241485596},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7330614328384399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7075300216674805},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7041088938713074},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4779134690761566},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4770828187465668},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46837741136550903},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.4459387958049774},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.11375659704208374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8670885562896729},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.8610374927520752},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.7364609241485596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7330614328384399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7075300216674805},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7041088938713074},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4779134690761566},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4770828187465668},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46837741136550903},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4459387958049774},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.11375659704208374}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1162/089120103322753356","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322753356","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120103322753356","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:repository.upenn.edu:dissertations-1896","is_oa":false,"landing_page_url":"https://repository.upenn.edu/dissertations/AAI9926110","pdf_url":null,"source":{"id":"https://openalex.org/S4377196331","display_name":"Scholarly Commons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dissertations available from ProQuest","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.416.3677","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.416.3677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.public.asu.edu/~jzhou29/MLNLP/papers/zettlemoyer/dissertation/Michael Collins-thesis.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.5668","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.5668","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/J/J03/J03-4003.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.57.9525","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.57.9525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.mit.edu/people/mcollins/papers/CL2003.ps","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:bae78c9ab99a418db69c53e4b2a25a4e","is_oa":false,"landing_page_url":"https://doaj.org/article/bae78c9ab99a418db69c53e4b2a25a4e","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 29, Iss 4 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120103322753356","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322753356","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120103322753356","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","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2092654472.pdf","grobid_xml":"https://content.openalex.org/works/W2092654472.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W79411081","https://openalex.org/W131829211","https://openalex.org/W199541590","https://openalex.org/W1491745322","https://openalex.org/W1508191042","https://openalex.org/W1509045587","https://openalex.org/W1535015163","https://openalex.org/W1567570606","https://openalex.org/W1574901103","https://openalex.org/W1585559843","https://openalex.org/W1598003989","https://openalex.org/W1600844763","https://openalex.org/W1601728146","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1809152426","https://openalex.org/W1936920915","https://openalex.org/W1972573551","https://openalex.org/W1982944197","https://openalex.org/W1986543644","https://openalex.org/W1993750641","https://openalex.org/W1994507518","https://openalex.org/W2002089154","https://openalex.org/W2004673890","https://openalex.org/W2005505724","https://openalex.org/W2039240651","https://openalex.org/W2052449326","https://openalex.org/W2069912724","https://openalex.org/W2074260075","https://openalex.org/W2077613835","https://openalex.org/W2087165009","https://openalex.org/W2093647425","https://openalex.org/W2096466920","https://openalex.org/W2102924265","https://openalex.org/W2104029044","https://openalex.org/W2104399512","https://openalex.org/W2110607519","https://openalex.org/W2110651511","https://openalex.org/W2110882317","https://openalex.org/W2111041233","https://openalex.org/W2113641473","https://openalex.org/W2114886551","https://openalex.org/W2123893795","https://openalex.org/W2134666210","https://openalex.org/W2138389163","https://openalex.org/W2139895384","https://openalex.org/W2147880316","https://openalex.org/W2153439141","https://openalex.org/W2155693943","https://openalex.org/W2161160885","https://openalex.org/W2163918411","https://openalex.org/W2166451556","https://openalex.org/W2167434254","https://openalex.org/W2309755354","https://openalex.org/W2949237929","https://openalex.org/W2952654140","https://openalex.org/W2963847008","https://openalex.org/W3021452258","https://openalex.org/W3021713638","https://openalex.org/W3088560083","https://openalex.org/W4231741839","https://openalex.org/W4241850027","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1523666900","https://openalex.org/W2367925007","https://openalex.org/W3015724364","https://openalex.org/W4288263119","https://openalex.org/W2967994095","https://openalex.org/W2900126711","https://openalex.org/W4285240985","https://openalex.org/W4225162083","https://openalex.org/W3202115945","https://openalex.org/W2542958340"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"three":[3],"statistical":[4],"models":[5,11,85,103,143,167],"for":[6,69],"natural":[7],"language":[8],"parsing.":[9],"The":[10,84],"extend":[12],"methods":[13],"from":[14],"probabilistic":[15],"context-free":[16],"grammars":[17],"to":[18,22,37,49,168,174,179],"lexicalized":[19],"grammars,":[20],"leading":[21],"approaches":[23],"in":[24,104,131,155,186],"which":[25],"a":[26,38,109,126],"parse":[27],"tree":[28],"is":[29,99],"represented":[30],"as":[31,123,125],"the":[32,43,53,89,105,113,142,156,166,176,184,189],"sequence":[33],"of":[34,42,58,61,73,112,128,135,141,152,183,188],"decisions":[35],"corresponding":[36],"head-centered,":[39],"top-down":[40],"derivation":[41],"tree.":[44],"Independence":[45],"assumptions":[46],"then":[47],"lead":[48],"parameters":[50],"that":[51,96,170],"encode":[52],"X-bar":[54],"schema,":[55],"subcategorization,":[56],"ordering":[57],"complements,":[59],"placement":[60],"adjuncts,":[62],"bigram":[63],"lexical":[64,82],"dependencies,":[65],"wh-movement,":[66],"and":[67,158],"preferences":[68,75],"close":[70],"attachment.":[71],"All":[72],"these":[74],"are":[76,86],"expressed":[77],"by":[78,149],"probabilities":[79],"conditioned":[80],"on":[81,88,119,146],"heads.":[83],"evaluated":[87],"Penn":[90],"Wall":[91],"Street":[92],"Journal":[93],"Treebank,":[94],"showing":[95],"their":[97],"accuracy":[98],"competitive":[100],"with":[101],"other":[102],"literature.":[106],"To":[107],"gain":[108],"better":[110],"understanding":[111],"models,":[114],"we":[115,164],"also":[116],"give":[117,180],"results":[118,130],"different":[120],"constituent":[121],"types,":[122],"well":[124],"breakdown":[127],"precision/recall":[129],"recovering":[132],"various":[133,139,153,190],"types":[134],"dependencies.":[136],"We":[137],"analyze":[138],"characteristics":[140],"through":[144,159],"experiments":[145],"parsing":[147,175],"accuracy,":[148],"collecting":[150],"frequencies":[151],"structures":[154],"treebank,":[157,177],"linguistically":[160],"motivated":[161],"examples.":[162],"Finally,":[163],"compare":[165],"others":[169],"have":[171],"been":[172],"applied":[173],"aiming":[178],"some":[181],"explanation":[182],"difference":[185],"performance":[187],"models.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":43},{"year":2016,"cited_by_count":52},{"year":2015,"cited_by_count":67},{"year":2014,"cited_by_count":83},{"year":2013,"cited_by_count":141},{"year":2012,"cited_by_count":96}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}