{"id":"https://openalex.org/W2014516359","doi":"https://doi.org/10.1162/089120103322711569","title":"Introduction to the Special Issue on the Web as Corpus","display_name":"Introduction to the Special Issue on the Web as Corpus","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2014516359","doi":"https://doi.org/10.1162/089120103322711569","mag":"2014516359"},"language":"en","primary_location":{"id":"doi:10.1162/089120103322711569","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322711569","pdf_url":"https://direct.mit.edu/coli/article-pdf/29/3/333/1798148/089120103322711569.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/29/3/333/1798148/089120103322711569.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064159344","display_name":"Adam Kilgarriff","orcid":null},"institutions":[{"id":"https://openalex.org/I71637028","display_name":"University of Brighton","ror":"https://ror.org/04kp2b655","country_code":"GB","type":"education","lineage":["https://openalex.org/I71637028"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Adam Kilgarriff","raw_affiliation_strings":["Lexicography MasterClass Ltd. and ITRI University of Brighton, Lewes Rd, Brighton, BN2 4JG, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lexicography MasterClass Ltd. and ITRI University of Brighton, Lewes Rd, Brighton, BN2 4JG, UK","institution_ids":["https://openalex.org/I71637028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039513155","display_name":"Gregory Grefenstette","orcid":"https://orcid.org/0000-0001-8479-049X"},"institutions":[{"id":"https://openalex.org/I4210155069","display_name":"Clairvoyant Technology (United States)","ror":"https://ror.org/04m281x40","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155069"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Grefenstette","raw_affiliation_strings":["Clairvoyance Corporation, Suite 700, 5001 Baum Blvd, Pittsburgh, PA 15213-1854"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clairvoyance Corporation, Suite 700, 5001 Baum Blvd, Pittsburgh, PA 15213-1854","institution_ids":["https://openalex.org/I4210155069"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064159344"],"corresponding_institution_ids":["https://openalex.org/I71637028"],"apc_list":null,"apc_paid":null,"fwci":87.2456,"has_fulltext":true,"cited_by_count":925,"citation_normalized_percentile":{"value":0.99914463,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":"3","first_page":"333","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13976","display_name":"Web visibility and informetrics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13976","display_name":"Web visibility and informetrics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13155","display_name":"Digital Communication and Language","score":0.9017999768257141,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7575253844261169},{"id":"https://openalex.org/keywords/dream","display_name":"Dream","score":0.5659271478652954},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5206776857376099},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4464094042778015},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4311865270137787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3734365701675415},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33392733335494995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3276088833808899},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08834835886955261},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08380827307701111}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575253844261169},{"id":"https://openalex.org/C2781095916","wikidata":"https://www.wikidata.org/wiki/Q36348","display_name":"Dream","level":2,"score":0.5659271478652954},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5206776857376099},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4464094042778015},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4311865270137787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3734365701675415},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33392733335494995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3276088833808899},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08834835886955261},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08380827307701111},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/089120103322711569","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322711569","pdf_url":"https://direct.mit.edu/coli/article-pdf/29/3/333/1798148/089120103322711569.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:10.1.1.104.6130","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.6130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.halskov.net/files/Kilgarriff_web_as_corpus.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.117.3380","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.117.3380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mitpress.mit.edu/journals/pdf/coli_29_3_333_0.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.4113","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.4113","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/J03-3001.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:057f5c5e5a3345d0a92b3796ade6b7bb","is_oa":false,"landing_page_url":"https://doaj.org/article/057f5c5e5a3345d0a92b3796ade6b7bb","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 3 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120103322711569","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103322711569","pdf_url":"https://direct.mit.edu/coli/article-pdf/29/3/333/1798148/089120103322711569.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":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2014516359.pdf","grobid_xml":"https://content.openalex.org/works/W2014516359.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W151117666","https://openalex.org/W170619969","https://openalex.org/W199541590","https://openalex.org/W1481381758","https://openalex.org/W1489384387","https://openalex.org/W1489834179","https://openalex.org/W1490022694","https://openalex.org/W1506298239","https://openalex.org/W1540931780","https://openalex.org/W1548204228","https://openalex.org/W1574901103","https://openalex.org/W1633771733","https://openalex.org/W1634615364","https://openalex.org/W1659541576","https://openalex.org/W1784531618","https://openalex.org/W1803932089","https://openalex.org/W1949782377","https://openalex.org/W1979541840","https://openalex.org/W2006734720","https://openalex.org/W2007709031","https://openalex.org/W2020747601","https://openalex.org/W2038201841","https://openalex.org/W2073272771","https://openalex.org/W2074952134","https://openalex.org/W2088198454","https://openalex.org/W2093519373","https://openalex.org/W2093585241","https://openalex.org/W2099685860","https://openalex.org/W2104232304","https://openalex.org/W2114930830","https://openalex.org/W2115054880","https://openalex.org/W2115792525","https://openalex.org/W2126414663","https://openalex.org/W2136028896","https://openalex.org/W2138491396","https://openalex.org/W2145080939","https://openalex.org/W2146888100","https://openalex.org/W2157963512","https://openalex.org/W2166084599","https://openalex.org/W2221553715","https://openalex.org/W2817959856","https://openalex.org/W2949696181","https://openalex.org/W4211148787"],"related_works":["https://openalex.org/W1762480892","https://openalex.org/W597599663","https://openalex.org/W4205387075","https://openalex.org/W1537165133","https://openalex.org/W2390579330","https://openalex.org/W1578892932","https://openalex.org/W2387132837","https://openalex.org/W2369963050","https://openalex.org/W2807829757","https://openalex.org/W2357117347"],"abstract_inverted_index":{"The":[0],"Web,":[1],"teeming":[2],"as":[3],"it":[4],"is":[5,22,39],"with":[6],"language":[7],"data,":[8],"of":[9,12,30],"all":[10],"manner":[11],"varieties":[13],"and":[14,19],"languages,":[15],"in":[16,35],"vast":[17],"quantity":[18],"freely":[20],"available,":[21],"a":[23],"fabulous":[24],"linguists'":[25],"playground.":[26],"This":[27],"special":[28],"issue":[29],"Computational":[31],"Linguistics":[32],"explores":[33],"ways":[34],"which":[36],"this":[37],"dream":[38],"being":[40],"explored.":[41]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":58},{"year":2018,"cited_by_count":48},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":57},{"year":2015,"cited_by_count":41},{"year":2014,"cited_by_count":67},{"year":2013,"cited_by_count":82},{"year":2012,"cited_by_count":41}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}
