{"id":"https://openalex.org/W2144087279","doi":"https://doi.org/10.3115/1073083.1073165","title":"Ranking algorithms for named-entity extraction","display_name":"Ranking algorithms for named-entity extraction","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2144087279","doi":"https://doi.org/10.3115/1073083.1073165","mag":"2144087279"},"language":"en","primary_location":{"id":"doi:10.3115/1073083.1073165","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073165","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073165","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","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/10.3115/1073083.1073165","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079061237","display_name":"Michael Collins","orcid":"https://orcid.org/0000-0003-0997-1527"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Collins","raw_affiliation_strings":["AT&T Labs-Research, New Jersey","AT&T Labs-Research, New Jersey#TAB#"],"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research, New Jersey","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs-Research, New Jersey#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079061237"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":13.6873,"has_fulltext":true,"cited_by_count":241,"citation_normalized_percentile":{"value":0.98748921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"489","last_page":"489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.998199999332428,"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":0.9970999956130981,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7748818397521973},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7741944789886475},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6326987147331238},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.601033627986908},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.586563766002655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4907558858394623},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.46383628249168396},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4559711515903473},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4531053900718689},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4451524019241333},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4186372756958008},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39912140369415283},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15513020753860474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748818397521973},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7741944789886475},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6326987147331238},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.601033627986908},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.586563766002655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4907558858394623},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.46383628249168396},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4559711515903473},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4531053900718689},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4451524019241333},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4186372756958008},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39912140369415283},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15513020753860474},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1073083.1073165","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073165","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073165","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1073083.1073165","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073165","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073165","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2144087279.pdf","grobid_xml":"https://content.openalex.org/works/W2144087279.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1520377376","https://openalex.org/W1528620860","https://openalex.org/W1552767446","https://openalex.org/W1563088657","https://openalex.org/W1575332430","https://openalex.org/W1734853756","https://openalex.org/W1773803948","https://openalex.org/W1934019294","https://openalex.org/W1979711143","https://openalex.org/W2008652694","https://openalex.org/W2040870580","https://openalex.org/W2068537423","https://openalex.org/W2092654472","https://openalex.org/W2098379588","https://openalex.org/W2121127625","https://openalex.org/W2127713198","https://openalex.org/W2131297983","https://openalex.org/W2147880316","https://openalex.org/W2160842254","https://openalex.org/W2309755354","https://openalex.org/W3021452258","https://openalex.org/W4285719527","https://openalex.org/W6637295340","https://openalex.org/W6679091061"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W4239608116","https://openalex.org/W2002382339","https://openalex.org/W1509860440","https://openalex.org/W2119157339"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"algorithms":[3,47],"which":[4],"rerank":[5],"the":[6,14,17,42,53],"top":[7],"N":[8],"hypotheses":[9],"from":[10],"a":[11,23,32],"maximum-entropy":[12,54],"tagger,":[13],"application":[15],"being":[16],"recovery":[18],"of":[19,25],"named-entity":[20],"boundaries":[21],"in":[22,70],"corpus":[24],"web":[26],"data.":[27],"The":[28,38,56],"first":[29],"approach":[30,40],"uses":[31,41],"boosting":[33],"algorithm":[34,59],"for":[35],"ranking":[36],"problems.":[37],"second":[39],"voted":[43,57],"perceptron":[44,58],"algorithm.":[45],"Both":[46],"give":[48],"comparable,":[49],"significant":[50],"improvements":[51],"over":[52],"baseline.":[55],"can":[60],"be":[61],"considerably":[62],"more":[63],"efficient":[64],"to":[65],"train,":[66],"at":[67],"some":[68],"cost":[69],"computation":[71],"on":[72],"test":[73],"examples.":[74]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":16}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}