{"id":"https://openalex.org/W2025214515","doi":"https://doi.org/10.1162/089120100561719","title":"Extracting the Lowest-Frequency Words: Pitfalls and Possibilities","display_name":"Extracting the Lowest-Frequency Words: Pitfalls and Possibilities","publication_year":2000,"publication_date":"2000-09-01","ids":{"openalex":"https://openalex.org/W2025214515","doi":"https://doi.org/10.1162/089120100561719","mag":"2025214515"},"language":"en","primary_location":{"id":"doi:10.1162/089120100561719","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120100561719","pdf_url":"https://direct.mit.edu/coli/article-pdf/26/3/301/1797527/089120100561719.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/26/3/301/1797527/089120100561719.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061783958","display_name":"Marc Weeber","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marc Weeber","raw_affiliation_strings":["University of Groningen, Groningen University Institute for Drug Exploration, Department of Social Pharmacy and Pharmacoepidemiology, Ant. Deusinglaan 1, 9713 AV Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen University Institute for Drug Exploration, Department of Social Pharmacy and Pharmacoepidemiology, Ant. Deusinglaan 1, 9713 AV Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001224245","display_name":"Rein Vos","orcid":"https://orcid.org/0000-0002-5034-3568"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]},{"id":"https://openalex.org/I4210114239","display_name":"Department of Health","ror":"https://ror.org/0225asj53","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210114239"]}],"countries":["NL","TW"],"is_corresponding":false,"raw_author_name":"Rein Vos","raw_affiliation_strings":["University of Groningen, University of Maastricht, Faculty of Health Sciences, Department of Health Ethics and Philosophy, P.O. Box 616, 6200 MD, Maastricht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Groningen, University of Maastricht, Faculty of Health Sciences, Department of Health Ethics and Philosophy, P.O. Box 616, 6200 MD, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I4210114239","https://openalex.org/I34352273"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087366961","display_name":"R. Harald Baayen","orcid":"https://orcid.org/0000-0003-3178-3944"},"institutions":[{"id":"https://openalex.org/I4210089003","display_name":"Max Planck Institute for Psycholinguistics","ror":"https://ror.org/00671me87","country_code":"NL","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210089003"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"R. Harald Baayen","raw_affiliation_strings":["Max Planck Institute for Psycholinguistics, Max Planck Institute for Psycholinguistics, P.O. Box 310, 6500 AH Nijmegen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Psycholinguistics, Max Planck Institute for Psycholinguistics, P.O. Box 310, 6500 AH Nijmegen","institution_ids":["https://openalex.org/I4210089003"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7327,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94813614,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":"3","first_page":"301","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.965399980545044,"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":0.965399980545044,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9358000159263611,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9153000116348267,"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/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.7238205075263977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6561872363090515},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6155950427055359},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5113000869750977},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.48320090770721436},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4812350273132324},{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.47259196639060974},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.46636614203453064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4599640965461731},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.44559434056282043},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.38829588890075684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34830066561698914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33870893716812134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12177059054374695},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08694830536842346}],"concepts":[{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.7238205075263977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6561872363090515},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6155950427055359},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5113000869750977},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.48320090770721436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4812350273132324},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.47259196639060974},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.46636614203453064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4599640965461731},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.44559434056282043},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.38829588890075684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34830066561698914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33870893716812134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12177059054374695},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08694830536842346},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1162/089120100561719","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120100561719","pdf_url":"https://direct.mit.edu/coli/article-pdf/26/3/301/1797527/089120100561719.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:pure.rug.nl:openaire/e2bc30c2-fb43-4ecb-ac16-1dc7c531f72b","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/e2bc30c2-fb43-4ecb-ac16-1dc7c531f72b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Weeber, M, Vos, R & Baayen, RH 2000, 'Extracting the lowest-frequency words: Pitfalls and possibilities', Computational Linguistics, vol. 26, no. 3, pp. 301-317. https://doi.org/10.1162/089120100561719","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.rug.nl:publications/e2bc30c2-fb43-4ecb-ac16-1dc7c531f72b","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/e2bc30c2-fb43-4ecb-ac16-1dc7c531f72b","pdf_url":"https://pure.rug.nl/ws/files/59390643/089120100561719.pdf","source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Weeber, M, Vos, R & Baayen, RH 2000, 'Extracting the lowest-frequency words: Pitfalls and possibilities', Computational Linguistics, vol. 26, no. 3, pp. 301-317. https://doi.org/10.1162/089120100561719","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.2834","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.2834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://pami.uwaterloo.ca/~nwanas/ftp/Lingusitics/weeber00.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.6302","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.6302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lhncbc.nlm.nih.gov/lhc/docs/published/2000/pub2000060.pdf","raw_type":"text"},{"id":"pmh:oai:acl.sr.language-archives.org:J00-3001","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/J00-3001","pdf_url":null,"source":{"id":"https://openalex.org/S4306402137","display_name":"The COCOON platform (University of Paris)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:doaj.org/article:9a59e3a10a55474088a864a18a972b90","is_oa":false,"landing_page_url":"https://doaj.org/article/9a59e3a10a55474088a864a18a972b90","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 26, Iss 3 (2021)","raw_type":"article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/173398","is_oa":false,"landing_page_url":"http://hdl.handle.net/2066/173398","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, 26.3, pp. 301-317","raw_type":"Article / Letter to editor"}],"best_oa_location":{"id":"doi:10.1162/089120100561719","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120100561719","pdf_url":"https://direct.mit.edu/coli/article-pdf/26/3/301/1797527/089120100561719.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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2025214515.pdf","grobid_xml":"https://content.openalex.org/works/W2025214515.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1557914122","https://openalex.org/W1593045043","https://openalex.org/W1940278502","https://openalex.org/W2002374079","https://openalex.org/W2007709031","https://openalex.org/W2031762965","https://openalex.org/W2105562985","https://openalex.org/W2116780029","https://openalex.org/W2152311076","https://openalex.org/W2422766945","https://openalex.org/W2918232142","https://openalex.org/W2997757304","https://openalex.org/W3021510377","https://openalex.org/W3031337294"],"related_works":["https://openalex.org/W2386544544","https://openalex.org/W2033530841","https://openalex.org/W2976460499","https://openalex.org/W3120840132","https://openalex.org/W2155023705","https://openalex.org/W2519555118","https://openalex.org/W2403014995","https://openalex.org/W2729076615","https://openalex.org/W4233711294","https://openalex.org/W2095577376"],"abstract_inverted_index":{"In":[0],"a":[1,21,72,104,160],"medical":[2],"information":[3],"extraction":[4,43,109,125,182],"system,":[5],"we":[6],"use":[7],"common":[8],"word":[9,48],"association":[10,57],"techniques":[11],"to":[12,111,173],"extract":[13,174],"side-effect-related":[14],"terms.":[15],"Many":[16],"of":[17,23,56,68,82,94,115,170],"these":[18,88],"terms":[19],"have":[20],"frequency":[22,49],"less":[24],"than":[25],"five.":[26],"Standard":[27],"word-association-based":[28,124],"applications":[29],"disregard":[30,36],"the":[31,46,54,59,69,80,91,95,113,116,133,146,163,168,171,181],"lowest-frequency":[32,96,134],"words,":[33,135],"and":[34,62,79,106,166],"hence":[35],"useful":[37],"information.":[38],"We":[39,85,98,119],"therefore":[40],"devised":[41],"an":[42],"system":[44,52,70],"for":[45,145],"full":[47],"range.":[50],"This":[51],"computes":[53],"significance":[55,137],"by":[58,90,130],"log-likelihood":[60],"ratio":[61],"Fisher's":[63],"exact":[64],"test.":[65],"The":[66],"output":[67],"shows":[71],"recurrent,":[73],"corpus-independent":[74],"pattern":[75],"in":[76,162,178],"both":[77],"recall":[78],"number":[81],"significant":[83],"words.":[84,97],"will":[86,120],"explain":[87],"patterns":[89],"statistical":[92,164],"behavior":[93],"used":[99],"Dutch":[100],"verb-particle":[101],"combinations":[102],"as":[103],"second":[105],"independent":[107],"collocation":[108],"application":[110],"illustrate":[112],"generality":[114],"observed":[117],"phenomena.":[118],"conclude":[121],"that":[122],"a)":[123],"systems":[126],"can":[127],"be":[128,141,158,176],"enhanced":[129],"also":[131],"considering":[132],"b)":[136],"levels":[138],"should":[139,157,175],"not":[140],"fixed":[142],"but":[143],"adjusted":[144],"optimal":[147],"window":[148],"size,":[149],"c)":[150],"hapax":[151],"legomena,":[152],"words":[153],"occurring":[154],"only":[155],"once,":[156],"disregarded":[159],"priori":[161],"analysis,":[165],"d)":[167],"distribution":[169],"targets":[172],"considered":[177],"combination":[179],"with":[180],"method.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}