{"id":"https://openalex.org/W2124416056","doi":"https://doi.org/10.1162/089120103322711604","title":"Using the Web to Obtain Frequencies for Unseen Bigrams","display_name":"Using the Web to Obtain Frequencies for Unseen Bigrams","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2124416056","doi":"https://doi.org/10.1162/089120103322711604","mag":"2124416056"},"language":"en","primary_location":{"id":"doi:10.1162/089120103322711604","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322711604","pdf_url":"https://direct.mit.edu/coli/article-pdf/29/3/459/1798134/089120103322711604.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/29/3/459/1798134/089120103322711604.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054936589","display_name":"Frank Keller","orcid":"https://orcid.org/0000-0002-8242-4362"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Frank Keller","raw_affiliation_strings":["University of Edinburgh, School of Informatics, 2 Buccleuch Place, Edinburgh EH8 9LW, UK","School of Informatics, University of Edinburgh, 2 Buccleuch Place, Edinburgh, EH8 9LW, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, School of Informatics, 2 Buccleuch Place, Edinburgh EH8 9LW, UK","institution_ids":[]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, 2 Buccleuch Place, Edinburgh, EH8 9LW, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041024491","display_name":"Mirella Lapata","orcid":"https://orcid.org/0000-0002-2107-1516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirella Lapata","raw_affiliation_strings":["University of Sheffield, Department of Computer Science, 211 Portobello Street, Sheffield S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"University of Sheffield, Department of Computer Science, 211 Portobello Street, Sheffield S1 4DP, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054936589"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":36.0332,"has_fulltext":true,"cited_by_count":357,"citation_normalized_percentile":{"value":0.99797036,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":"3","first_page":"459","last_page":"484"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9922000169754028,"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/bigram","display_name":"Bigram","score":0.9841804504394531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7431561946868896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5709152221679688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5326563715934753},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.5069389939308167},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4956716299057007},{"id":"https://openalex.org/keywords/adjective","display_name":"Adjective","score":0.4904620349407196},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.44313228130340576},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.429929256439209},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.427796334028244},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4171590209007263},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.41032126545906067},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41004621982574463},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3801470994949341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3243861198425293},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2446744740009308},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17304077744483948},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.1423419713973999},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06860041618347168}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9841804504394531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7431561946868896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5709152221679688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5326563715934753},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.5069389939308167},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4956716299057007},{"id":"https://openalex.org/C2777683214","wikidata":"https://www.wikidata.org/wiki/Q34698","display_name":"Adjective","level":3,"score":0.4904620349407196},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.44313228130340576},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.429929256439209},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.427796334028244},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4171590209007263},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.41032126545906067},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41004621982574463},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3801470994949341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3243861198425293},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2446744740009308},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17304077744483948},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.1423419713973999},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06860041618347168},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/089120103322711604","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322711604","pdf_url":"https://direct.mit.edu/coli/article-pdf/29/3/459/1798134/089120103322711604.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:10.1.1.75.6963","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.6963","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/J03-3005.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.99.7967","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.7967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/keller/papers/cl03.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:ce07080407d443ee9b15bc3a8d89e909","is_oa":true,"landing_page_url":"https://doaj.org/article/ce07080407d443ee9b15bc3a8d89e909","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 29, Iss 3 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120103322711604","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322711604","pdf_url":"https://direct.mit.edu/coli/article-pdf/29/3/459/1798134/089120103322711604.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","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323322","display_name":"Universit\u00e4t des Saarlandes","ror":"https://ror.org/01jdpyv68"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2124416056.pdf","grobid_xml":"https://content.openalex.org/works/W2124416056.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W73274768","https://openalex.org/W1489384387","https://openalex.org/W1516391399","https://openalex.org/W1540931780","https://openalex.org/W1592405359","https://openalex.org/W1593239840","https://openalex.org/W1622422412","https://openalex.org/W1704669313","https://openalex.org/W1733633583","https://openalex.org/W1735182246","https://openalex.org/W1754931551","https://openalex.org/W1859173823","https://openalex.org/W1950936596","https://openalex.org/W1991158387","https://openalex.org/W1998641229","https://openalex.org/W2003698958","https://openalex.org/W2007695588","https://openalex.org/W2024988999","https://openalex.org/W2027666258","https://openalex.org/W2031344788","https://openalex.org/W2033586051","https://openalex.org/W2035967403","https://openalex.org/W2038248725","https://openalex.org/W2038826915","https://openalex.org/W2048021297","https://openalex.org/W2064070185","https://openalex.org/W2068017609","https://openalex.org/W2069185229","https://openalex.org/W2073677209","https://openalex.org/W2088198454","https://openalex.org/W2094276686","https://openalex.org/W2102381086","https://openalex.org/W2104232304","https://openalex.org/W2115983295","https://openalex.org/W2119610041","https://openalex.org/W2120084270","https://openalex.org/W2121545956","https://openalex.org/W2127314673","https://openalex.org/W2129626314","https://openalex.org/W2132024321","https://openalex.org/W2132851324","https://openalex.org/W2133702079","https://openalex.org/W2134237567","https://openalex.org/W2143413399","https://openalex.org/W2145080939","https://openalex.org/W2157963512","https://openalex.org/W2161383849","https://openalex.org/W2161821575","https://openalex.org/W2163953154","https://openalex.org/W2165897980","https://openalex.org/W2183330546","https://openalex.org/W2213505007","https://openalex.org/W2235903980","https://openalex.org/W2295081780","https://openalex.org/W2725872906","https://openalex.org/W3087838514","https://openalex.org/W4231162912","https://openalex.org/W4241850027","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4312381793","https://openalex.org/W2385963184","https://openalex.org/W2350058787","https://openalex.org/W3139255945","https://openalex.org/W2976849154","https://openalex.org/W3112308623","https://openalex.org/W2902614234","https://openalex.org/W2068167831","https://openalex.org/W4388156376","https://openalex.org/W2745526283"],"abstract_inverted_index":{"This":[0],"article":[1],"shows":[2],"that":[3,14],"the":[4,35],"Web":[5,36,53,63,73,86],"can":[6],"be":[7],"employed":[8],"to":[9],"obtain":[10],"frequencies":[11,54,64,74,76,87],"for":[12,25,28],"bigrams":[13,33],"are":[15],"unseen":[16],"in":[17,88],"a":[18,23,39,49,59,69,82,89],"given":[19],"corpus.":[20],"We":[21,42],"describe":[22],"method":[24,45],"retrieving":[26],"counts":[27],"adjective-noun,":[29],"noun-noun,":[30],"and":[31,55,65,75],"verb-object":[32],"from":[34],"by":[37,46],"querying":[38],"search":[40],"engine.":[41],"evaluate":[43],"this":[44],"demonstrating:":[47],"(a)":[48],"high":[50],"correlation":[51,61,71],"between":[52,62,72],"corpus":[56],"frequencies;":[57],"(b)":[58],"reliable":[60,70],"plausibility":[66],"judgments;":[67],"(c)":[68],"recreated":[77],"using":[78],"class-based":[79],"smoothing;":[80],"(d)":[81],"good":[83],"performance":[84],"of":[85],"pseudo":[90],"disambiguation":[91],"task.":[92]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":30}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
