{"id":"https://openalex.org/W1998324505","doi":"https://doi.org/10.3115/1118693.1118722","title":"Ensemble methods for automatic thesaurus extraction","display_name":"Ensemble methods for automatic thesaurus extraction","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W1998324505","doi":"https://doi.org/10.3115/1118693.1118722","mag":"1998324505"},"language":"en","primary_location":{"id":"doi:10.3115/1118693.1118722","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118722","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118722&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '02","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1118722&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024711700","display_name":"James Curran","orcid":"https://orcid.org/0000-0001-9637-0484"},"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":"James R. Curran","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom","University of Edinburgh, edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh, edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024711700"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.983,"has_fulltext":true,"cited_by_count":71,"citation_normalized_percentile":{"value":0.91540127,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"222","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7820439338684082},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.713935136795044},{"id":"https://openalex.org/keywords/thesaurus","display_name":"Thesaurus","score":0.6965746879577637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.596176266670227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5710804462432861},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4544163644313812},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4277697205543518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820439338684082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.713935136795044},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.6965746879577637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.596176266670227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5710804462432861},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4544163644313812},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4277697205543518},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":3,"locations":[{"id":"doi:10.3115/1118693.1118722","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118722","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118722&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '02","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.7490","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.7490","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/W02/W02-1029.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.125.231","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.125.231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.it.usyd.edu.au/~james/pubs/pdf/emnlp02ensemble.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1118693.1118722","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118722","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118722&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '02","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1998324505.pdf","grobid_xml":"https://content.openalex.org/works/W1998324505.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W73274768","https://openalex.org/W1502523810","https://openalex.org/W1534477342","https://openalex.org/W1570059695","https://openalex.org/W1592073433","https://openalex.org/W1647729745","https://openalex.org/W1667986067","https://openalex.org/W1781980207","https://openalex.org/W2003698958","https://openalex.org/W2026779664","https://openalex.org/W2029858480","https://openalex.org/W2035967403","https://openalex.org/W2038721957","https://openalex.org/W2064580901","https://openalex.org/W2075645124","https://openalex.org/W2121227244","https://openalex.org/W2121545956","https://openalex.org/W2127314673","https://openalex.org/W2130636661","https://openalex.org/W2157963512","https://openalex.org/W2163953154","https://openalex.org/W2249186037","https://openalex.org/W2403515192","https://openalex.org/W2949524199","https://openalex.org/W2952828185","https://openalex.org/W4250516003"],"related_works":["https://openalex.org/W2046824966","https://openalex.org/W2358573687","https://openalex.org/W2100136642","https://openalex.org/W186704260","https://openalex.org/W2096290355","https://openalex.org/W1496588992","https://openalex.org/W266409346","https://openalex.org/W2075838610","https://openalex.org/W2184026322","https://openalex.org/W4213277595"],"abstract_inverted_index":{"Ensemble":[0],"methods":[1],"are":[2,36],"state":[3],"of":[4,41,57,74,92],"the":[5,39,53,75,87],"art":[6],"for":[7,52],"many":[8],"NLP":[9,93],"tasks.":[10],"Recent":[11],"work":[12,48],"by":[13,38],"Banko":[14],"and":[15,45,78],"Brill":[16],"(2001)":[17],"suggests":[18],"that":[19],"this":[20],"would":[21],"not":[22],"necessarily":[23],"be":[24],"true":[25],"if":[26],"very":[27,96],"large":[28,97],"training":[29],"corpora":[30],"were":[31],"available.":[32],"However,":[33],"their":[34,42],"results":[35,71],"limited":[37],"simplicity":[40],"evaluation":[43],"task":[44,56],"individual":[46],"classifiers.Our":[47],"explores":[49],"ensemble":[50],"efficacy":[51],"more":[54],"complex":[55],"automatic":[58],"thesaurus":[59],"extraction":[60],"on":[61,95],"up":[62],"to":[63,86],"300":[64],"million":[65],"words.":[66],"We":[67],"examine":[68],"our":[69],"conflicting":[70],"in":[72],"terms":[73],"constraints":[76],"on,":[77],"complexity":[79],"of,":[80],"different":[81],"contextual":[82],"representations,":[83],"which":[84],"contribute":[85],"sparseness-and":[88],"noise-induced":[89],"bias":[90],"behaviour":[91],"systems":[94],"corpora.":[98]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}