{"id":"https://openalex.org/W2042183662","doi":"https://doi.org/10.25596/jalc-2005-367","title":"A Consistent and Efficient Estimator for Data-Oriented Parsing","display_name":"A Consistent and Efficient Estimator for Data-Oriented Parsing","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2042183662","doi":"https://doi.org/10.25596/jalc-2005-367","mag":"2042183662"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.81.3513","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.3513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.illc.uva.nl/Publications/ResearchReports/MoL-2004-02.text.pdf","raw_type":"text"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.25596/jalc-2005-367","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045292328","display_name":"Andreas Zollmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zollmann, Andreas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034829413","display_name":"Khalil Sima\u2019an","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sima'an, Khalil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.4034,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.97237754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"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/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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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/parsing","display_name":"Parsing","score":0.7100926041603088},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5739018321037292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5610050559043884},{"id":"https://openalex.org/keywords/bottom-up-parsing","display_name":"Bottom-up parsing","score":0.44334176182746887},{"id":"https://openalex.org/keywords/top-down-parsing","display_name":"Top-down parsing","score":0.39941832423210144},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.36742478609085083},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36673659086227417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.258337140083313}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7100926041603088},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5739018321037292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5610050559043884},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.44334176182746887},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.39941832423210144},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36742478609085083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36673659086227417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.258337140083313}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.81.3513","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.3513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.illc.uva.nl/Publications/ResearchReports/MoL-2004-02.text.pdf","raw_type":"text"},{"id":"doi:10.25596/jalc-2005-367","is_oa":true,"landing_page_url":"https://doi.org/10.25596/jalc-2005-367","pdf_url":null,"source":{"id":"https://openalex.org/S62907800","display_name":"Journal of automata, languages and combinatorics","issn_l":"1430-189X","issn":["1430-189X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310313929","host_organization_name":"University of Giessen","host_organization_lineage":["https://openalex.org/P4310313929"],"host_organization_lineage_names":["University of Giessen"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.25596/jalc-2005-367","is_oa":true,"landing_page_url":"https://doi.org/10.25596/jalc-2005-367","pdf_url":null,"source":{"id":"https://openalex.org/S62907800","display_name":"Journal of automata, languages and combinatorics","issn_l":"1430-189X","issn":["1430-189X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310313929","host_organization_name":"University of Giessen","host_organization_lineage":["https://openalex.org/P4310313929"],"host_organization_lineage_names":["University of Giessen"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1497026191","https://openalex.org/W1539587067","https://openalex.org/W1541301615","https://openalex.org/W1574901103","https://openalex.org/W1608909294","https://openalex.org/W1632114991","https://openalex.org/W1976629384","https://openalex.org/W1992254746","https://openalex.org/W1994851566","https://openalex.org/W2047706513","https://openalex.org/W2104399512","https://openalex.org/W2105990715","https://openalex.org/W2120953952","https://openalex.org/W2134237567","https://openalex.org/W2148497595","https://openalex.org/W2161204834","https://openalex.org/W2587628976","https://openalex.org/W2802488870","https://openalex.org/W3150555252"],"related_works":["https://openalex.org/W1992254746","https://openalex.org/W2153653739","https://openalex.org/W2152263452","https://openalex.org/W2067694419","https://openalex.org/W2152302696","https://openalex.org/W1844099549","https://openalex.org/W1632114991","https://openalex.org/W2157762871","https://openalex.org/W1938853666","https://openalex.org/W1499470996","https://openalex.org/W2153568660","https://openalex.org/W2139621418","https://openalex.org/W2131297983","https://openalex.org/W2092654472","https://openalex.org/W1551104980","https://openalex.org/W2437005631","https://openalex.org/W2158388102","https://openalex.org/W2152600988","https://openalex.org/W2113075298","https://openalex.org/W1535015163"],"abstract_inverted_index":{"Given":[0],"a":[1,10,32,74,82,86,138,144,156],"sequence":[2,46],"of":[3,19,31,88,140,162,194,198],"samples":[4],"from":[5,25,79,115],"an":[6,16,116],"unknown":[7,41],"probability":[8],"distribution,":[9],"statistical":[11],"estimator":[12,34,98,127,134,158,170],"aims":[13],"at":[14],"providing":[15],"approximate":[17],"guess":[18,38],"the":[20,26,40,44,63,96,123,129,153,160,177,209],"distribution":[21,42],"by":[22,184],"utilizing":[23],"statistics":[24,80],"samples.":[27],"One":[28],"crucial":[29],"property":[30,50],"`good'":[33],"is":[35,51,77,101,111,135,171,182],"that":[36,95,112,166],"its":[37],"approaches":[39],"as":[43],"sample":[45],"grows":[47],"large.":[48],"This":[49,54,120],"called":[52],"consistency.":[53],"paper":[55,121],"concerns":[56],"estimators":[57],"for":[58,128,155,176],"natural":[59],"language":[60],"parsing":[61,147],"under":[62],"Data-":[64],"Oriented":[65],"Parsing":[66],"(DOP)":[67],"model.":[68,131],"The":[69,132],"DOP":[70,130,163,169],"model":[71],"specifies":[72],"how":[73],"probabilistic":[75],"grammar":[76],"acquired":[78],"over":[81],"given":[83],"training":[84],"treebank,":[85],"corpus":[87],"sentence-parse":[89],"pairs.":[90],"Recently,":[91],"Johnson":[92],"[15]":[93],"showed":[94],"BOP":[97],"(called":[99],"DOPl)":[100],"biased":[102,157],"and":[103,143,189,200],"inconsistent.":[104],"A":[105],"second":[106],"relevant":[107],"problem":[108],"with":[109,148,208],"DOP1":[110],"it":[113],"suffers":[114],"overwhelming":[117],"computational":[118,201],"inefficiency.":[119],"presents":[122],"first":[124],"(nontrivial)":[125],"consistent":[126],"new":[133,210],"based":[136],"on":[137],"combination":[139],"held-out":[141],"estimation":[142],"bias":[145,178],"toward":[146,179],"shorter":[149,180],"derivations.":[150],"To":[151],"justify":[152],"need":[154],"in":[159],"case":[161],"we":[164,203],"prove":[165],"every":[167],"non-overfitting":[168],"statistically":[172],"biased.":[173],"Our":[174],"choice":[175],"derivations":[181],"justified":[183],"empirical":[185],"experience,":[186],"mathematical":[187],"convenience":[188],"efficiency":[190],"considerations.":[191],"In":[192],"support":[193],"our":[195],"theoretical":[196],"results":[197,207],"consistency":[199],"efficiency,":[202],"also":[204],"report":[205],"experimental":[206],"estimator.":[211]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":40}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}