{"id":"https://openalex.org/W2168822971","doi":"https://doi.org/10.3115/1073083.1073105","title":"Active learning for statistical natural language parsing","display_name":"Active learning for statistical natural language parsing","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2168822971","doi":"https://doi.org/10.3115/1073083.1073105","mag":"2168822971"},"language":"en","primary_location":{"id":"doi:10.3115/1073083.1073105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073105","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073105","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/10.3115/1073083.1073105","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100659889","display_name":"Min Tang","orcid":"https://orcid.org/0000-0001-7323-3698"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Min Tang","raw_affiliation_strings":["Spoken Language Systems Group, Cambridge, Massachusetts"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Group, Cambridge, Massachusetts","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111895886","display_name":"Xiaoqiang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Luo","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043396055","display_name":"Salim Roukos","orcid":"https://orcid.org/0000-0003-2140-4349"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Salim Roukos","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100659889"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5465,"has_fulltext":true,"cited_by_count":180,"citation_normalized_percentile":{"value":0.96401652,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9923999905586243,"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":0.8692195415496826},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7754759788513184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7672977447509766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.724460780620575},{"id":"https://openalex.org/keywords/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.7163664698600769},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.555651843547821},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5264521241188049},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5223687291145325},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48375368118286133},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4572564661502838},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4400123953819275},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4261532127857208},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42088571190834045},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07593509554862976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8692195415496826},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7754759788513184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7672977447509766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.724460780620575},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.7163664698600769},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.555651843547821},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5264521241188049},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5223687291145325},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48375368118286133},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4572564661502838},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4400123953819275},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4261532127857208},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42088571190834045},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07593509554862976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1073083.1073105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073105","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073105","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.6256","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.6256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.lcs.mit.edu/sls/publications/2002/al_acl2002sub.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.8078","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.8078","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/P/P02/P02-1016.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1073083.1073105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073105","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073105","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":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2168822971.pdf","grobid_xml":"https://content.openalex.org/works/W2168822971.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W73418818","https://openalex.org/W170362076","https://openalex.org/W1508165687","https://openalex.org/W1514707997","https://openalex.org/W1528361845","https://openalex.org/W1553262910","https://openalex.org/W1560013842","https://openalex.org/W1567570606","https://openalex.org/W1797288984","https://openalex.org/W1810157568","https://openalex.org/W1927028487","https://openalex.org/W2069912724","https://openalex.org/W2076083849","https://openalex.org/W2107502455","https://openalex.org/W2110882317","https://openalex.org/W2114663556","https://openalex.org/W2121227244","https://openalex.org/W2137806537","https://openalex.org/W2570764145","https://openalex.org/W2963847008","https://openalex.org/W4236667607","https://openalex.org/W4285719527","https://openalex.org/W4310738704"],"related_works":["https://openalex.org/W3159631231","https://openalex.org/W4405590872","https://openalex.org/W4404624381","https://openalex.org/W4306248409","https://openalex.org/W4211213551","https://openalex.org/W2053943328","https://openalex.org/W3046984657","https://openalex.org/W2293063786","https://openalex.org/W2911292476","https://openalex.org/W2158873310"],"abstract_inverted_index":{"It":[0],"is":[1,19,52,61,105,113,121],"necessary":[2],"to":[3,9,28,39,63,97,154,163],"have":[4],"a":[5,11,17,26,103,156],"(large)":[6],"annotated":[7],"corpus":[8,18],"build":[10],"statistical":[12],"parser.":[13],"Acquisition":[14],"of":[15,42,67,94,135,158],"such":[16],"costly":[20],"and":[21,56,70,90],"time-consuming.":[22],"This":[23],"paper":[24],"presents":[25],"method":[27],"reduce":[29],"this":[30,78],"demand":[31],"using":[32],"active":[33,81],"learning,":[34],"which":[35],"selects":[36],"what":[37],"samples":[38,160],"annotate,":[40],"instead":[41],"annotating":[43],"blindly":[44],"the":[45,65,80,85,92,110,131,147,159,164],"whole":[46],"training":[47],"corpus.Sample":[48],"selection":[49,167],"for":[50,145],"annotation":[51],"based":[53],"upon":[54],"\"representativeness\"":[55],"\"usefulness\".":[57],"A":[58],"model-based":[59],"distance":[60],"proposed":[62],"measure":[64],"difference":[66],"two":[68],"sentences":[69],"their":[71],"most":[72],"likely":[73],"parse":[74],"trees.":[75],"Based":[76],"on":[77],"distance,":[79],"learning":[82],"process":[83],"analyzes":[84],"sample":[86,96],"distribution":[87],"by":[88,123],"clustering":[89],"calculates":[91],"density":[93],"each":[95],"quantify":[98],"its":[99,117],"representativeness.":[100],"Further":[101],"more,":[102],"sentence":[104],"deemed":[106],"as":[107,161],"useful":[108],"if":[109],"existing":[111],"model":[112],"highly":[114],"uncertain":[115],"about":[116,146],"parses,":[118],"where":[119],"uncertainty":[120],"measured":[122],"various":[124],"entropy-based":[125],"scores.Experiments":[126],"are":[127],"carried":[128],"out":[129],"in":[130],"shallow":[132],"semantic":[133],"parser":[134],"an":[136],"air":[137],"travel":[138],"dialog":[139],"system.":[140],"Our":[141],"result":[142],"shows":[143],"that":[144],"same":[148],"parsing":[149],"accuracy,":[150],"we":[151],"only":[152],"need":[153],"annotate":[155],"third":[157],"compared":[162],"usual":[165],"random":[166],"method.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}