{"id":"https://openalex.org/W1992254746","doi":"https://doi.org/10.1162/089120102317341783","title":"The DOP Estimation Method Is Biased and Inconsistent","display_name":"The DOP Estimation Method Is Biased and Inconsistent","publication_year":2002,"publication_date":"2002-03-01","ids":{"openalex":"https://openalex.org/W1992254746","doi":"https://doi.org/10.1162/089120102317341783","mag":"1992254746"},"language":"en","primary_location":{"id":"doi:10.1162/089120102317341783","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120102317341783","pdf_url":"https://direct.mit.edu/coli/article-pdf/28/1/71/1797696/089120102317341783.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/28/1/71/1797696/089120102317341783.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034461489","display_name":"Mark Johnson","orcid":"https://orcid.org/0000-0003-4809-8441"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark Johnson","raw_affiliation_strings":["Cognitive and Linguistic Sciences, Brown University, Providence, RI 02912"],"affiliations":[{"raw_affiliation_string":"Cognitive and Linguistic Sciences, Brown University, Providence, RI 02912","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034461489"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":6.3922,"has_fulltext":true,"cited_by_count":98,"citation_normalized_percentile":{"value":0.96712257,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"28","issue":"1","first_page":"71","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10320","display_name":"Neural Networks and Applications","score":0.9894000291824341,"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":0.8027840852737427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6638109087944031},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.608088493347168},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.5050738453865051},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46929794549942017},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4546315371990204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44717690348625183},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.41543442010879517},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3694959282875061},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23226016759872437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22923007607460022}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8027840852737427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638109087944031},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.608088493347168},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.5050738453865051},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46929794549942017},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4546315371990204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44717690348625183},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.41543442010879517},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3694959282875061},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23226016759872437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22923007607460022},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/089120102317341783","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120102317341783","pdf_url":"https://direct.mit.edu/coli/article-pdf/28/1/71/1797696/089120102317341783.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:10.1.1.20.2627","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.2627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://titan.cog.brown.edu:16080/~mj/papers/dop.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.22.5444","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.5444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cog.brown.edu/~mj/papers/dop.ps.gz","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:1b132cbd52a9422ab62c9540b92853f6","is_oa":true,"landing_page_url":"https://doaj.org/article/1b132cbd52a9422ab62c9540b92853f6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 28, Iss 1 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120102317341783","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120102317341783","pdf_url":"https://direct.mit.edu/coli/article-pdf/28/1/71/1797696/089120102317341783.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1992254746.pdf","grobid_xml":"https://content.openalex.org/works/W1992254746.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1495874564","https://openalex.org/W1539587067","https://openalex.org/W1734853756","https://openalex.org/W2076118331","https://openalex.org/W2099832412"],"related_works":["https://openalex.org/W1973480752","https://openalex.org/W2805502594","https://openalex.org/W4253208712","https://openalex.org/W1603677234","https://openalex.org/W3132641048","https://openalex.org/W2217679042","https://openalex.org/W2525971763","https://openalex.org/W2984753899","https://openalex.org/W4381248170","https://openalex.org/W3189621521"],"abstract_inverted_index":{"A":[0],"data-oriented":[1],"parsing":[2,8],"or":[3],"DOP":[4],"model":[5],"for":[6],"statistical":[7],"associates":[9],"fragments":[10],"of":[11,27,69],"linguistic":[12],"representations":[13],"with":[14],"numerical":[15],"weights,":[16],"where":[17],"these":[18],"weights":[19],"are":[20],"estimated":[21,55],"by":[22],"normalizing":[23],"the":[24,54,63,67,70],"empirical":[25],"frequency":[26],"each":[28],"fragment":[29],"in":[30,59],"a":[31],"training":[32,71],"corpus":[33,72],"(see":[34],"Bod":[35],"[1998]":[36],"and":[37,50],"references":[38],"cited":[39],"therein).":[40],"This":[41],"note":[42],"observes":[43],"that":[44,52],"this":[45],"estimation":[46],"method":[47],"is":[48],"biased":[49],"inconsistent":[51],"is,":[53],"distribution":[56,65],"does":[57],"not":[58],"general":[60],"converge":[61],"on":[62],"true":[64],"as":[66],"size":[68],"increases.":[73]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":36}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}