{"id":"https://openalex.org/W1967596232","doi":"https://doi.org/10.3115/1117794.1117795","title":"Pattern-based disambiguation for natural language processing","display_name":"Pattern-based disambiguation for natural language processing","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W1967596232","doi":"https://doi.org/10.3115/1117794.1117795","mag":"1967596232"},"language":"en","primary_location":{"id":"doi:10.3115/1117794.1117795","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117795","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117795","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117795","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018230694","display_name":"Eric Brill","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Eric Brill","raw_affiliation_strings":["Microsoft Research, Redmond, Wa","Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, Wa","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018230694"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":4.2436,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93958137,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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":0.9972000122070312,"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/ambiguity","display_name":"Ambiguity","score":0.8187720775604248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7954002618789673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6798005104064941},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6535226106643677},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6528178453445435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6405104398727417},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6369328498840332},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6060786843299866},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.508075475692749},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4283008873462677},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15551316738128662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12144246697425842},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10236498713493347}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.8187720775604248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954002618789673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6798005104064941},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6535226106643677},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6528178453445435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6405104398727417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6369328498840332},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6060786843299866},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.508075475692749},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4283008873462677},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15551316738128662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12144246697425842},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10236498713493347},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/1117794.1117795","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117795","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117795","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.6392","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.6392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.mit.edu/people/jimmylin/papers/Brill00.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.8864","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.8864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/~brill/Pubs/REG_EX.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.5006","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.5006","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/W/W00/W00-1301.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1117794.1117795","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117795","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117795","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"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/W1967596232.pdf","grobid_xml":"https://content.openalex.org/works/W1967596232.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1519443010","https://openalex.org/W1525582138","https://openalex.org/W1632114991","https://openalex.org/W1851901164","https://openalex.org/W2002089154","https://openalex.org/W2099345940","https://openalex.org/W2117400858","https://openalex.org/W2118996379","https://openalex.org/W2140842551","https://openalex.org/W2200350575","https://openalex.org/W2949201587","https://openalex.org/W2949237929","https://openalex.org/W2951328679","https://openalex.org/W2951797318","https://openalex.org/W3021713638","https://openalex.org/W4238633816","https://openalex.org/W4252676164","https://openalex.org/W4302339081","https://openalex.org/W6630968369","https://openalex.org/W6687517084"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W1516679419","https://openalex.org/W190396239"],"abstract_inverted_index":{"A":[0],"wide":[1],"range":[2],"of":[3,16],"natural":[4],"language":[5],"problems":[6],"can":[7,35],"be":[8,36],"viewed":[9],"as":[10],"disambiguating":[11],"between":[12],"a":[13,40,52],"small":[14],"set":[15,44],"alternatives":[17],"based":[18],"upon":[19],"the":[20,24,61,66],"string":[21,62],"context":[22],"surrounding":[23],"ambiguity":[25,67],"site.":[26],"In":[27],"this":[28],"paper":[29],"we":[30],"demonstrate":[31],"that":[32,54],"classification":[33],"accuracy":[34],"improved":[37],"by":[38,56],"invoking":[39],"more":[41],"descriptive":[42],"feature":[43],"than":[45],"what":[46],"is":[47],"typically":[48],"used.":[49],"We":[50],"present":[51],"technique":[53],"disambiguates":[55],"learning":[57],"regular":[58],"expressions":[59],"describing":[60],"contexts":[63],"in":[64],"which":[65],"sites":[68],"appear.":[69]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}