{"id":"https://openalex.org/W2158148237","doi":"https://doi.org/10.3115/1218955.1218962","title":"Discriminative language modeling with conditional random fields and the perceptron algorithm","display_name":"Discriminative language modeling with conditional random fields and the perceptron algorithm","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2158148237","doi":"https://doi.org/10.3115/1218955.1218962","mag":"2158148237"},"language":"en","primary_location":{"id":"doi:10.3115/1218955.1218962","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218962","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218962","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","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/10.3115/1218955.1218962","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020068498","display_name":"Brian Roark","orcid":null},"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":"Brian Roark","raw_affiliation_strings":["AT&T Labs -- Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"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":false,"raw_author_name":"Murat Saraclar","raw_affiliation_strings":["AT&T Labs -- Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079061237","display_name":"Michael Collins","orcid":"https://orcid.org/0000-0003-0997-1527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Collins","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034461489","display_name":"Mark Johnson","orcid":"https://orcid.org/0000-0003-4809-8441"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Johnson","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020068498"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":15.2502,"has_fulltext":true,"cited_by_count":139,"citation_normalized_percentile":{"value":0.98981014,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"es"},"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":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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/discriminative-model","display_name":"Discriminative model","score":0.8449738025665283},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7446414232254028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7125872373580933},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.6997014284133911},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.6202184557914734},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5698150396347046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5543566942214966},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5424803495407104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5405048727989197},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.532750129699707},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.5187171101570129},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5137782692909241},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4973278343677521},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44506335258483887},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.42358189821243286},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4053291976451874},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3105396032333374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17368915677070618}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8449738025665283},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7446414232254028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7125872373580933},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.6997014284133911},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.6202184557914734},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5698150396347046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5543566942214966},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5424803495407104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5405048727989197},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.532750129699707},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5187171101570129},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5137782692909241},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4973278343677521},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44506335258483887},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.42358189821243286},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4053291976451874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3105396032333374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17368915677070618},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.3115/1218955.1218962","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218962","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218962","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.100.4093","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.100.4093","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/acl2004/main/pdf/320_pdf_2-col.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1218955.1218962","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218962","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218962","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2158148237.pdf","grobid_xml":"https://content.openalex.org/works/W2158148237.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W8949146","https://openalex.org/W30564313","https://openalex.org/W90568776","https://openalex.org/W107761332","https://openalex.org/W605575788","https://openalex.org/W1481751294","https://openalex.org/W1491745322","https://openalex.org/W1979711143","https://openalex.org/W2005076803","https://openalex.org/W2008652694","https://openalex.org/W2034797903","https://openalex.org/W2046932483","https://openalex.org/W2097978681","https://openalex.org/W2098379588","https://openalex.org/W2102667697","https://openalex.org/W2114521167","https://openalex.org/W2114858359","https://openalex.org/W2124445791","https://openalex.org/W2132714218","https://openalex.org/W2141099517","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W3021430701","https://openalex.org/W4230318854","https://openalex.org/W4244046749"],"related_works":["https://openalex.org/W2055466819","https://openalex.org/W50079190","https://openalex.org/W2356597680","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2511246383","https://openalex.org/W2184553228"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"discriminative":[3],"language":[4],"modeling":[5],"for":[6,107],"a":[7,23,55,67,74,108],"large":[8],"vocabulary":[9],"speech":[10],"recognition":[11],"task.":[12],"We":[13],"contrast":[14],"two":[15],"parameter":[16],"estimation":[17],"methods:":[18],"the":[19,46,52,62,79,84,89,114],"perceptron":[20,59,90],"algorithm,":[21],"and":[22,41],"method":[24],"based":[25],"on":[26],"conditional":[27],"random":[28],"fields":[29],"(CRFs).":[30],"The":[31,58],"models":[32],"are":[33,42,51],"encoded":[34],"as":[35],"deterministic":[36],"weighted":[37],"finite":[38],"state":[39],"automata,":[40],"applied":[43],"by":[44],"intersecting":[45],"automata":[47],"with":[48,93],"word-lattices":[49],"that":[50],"output":[53,87],"from":[54,88,113],"baseline":[56,115],"recognizer.":[57],"algorithm":[60,91],"has":[61],"benefit":[63],"of":[64,76,116],"automatically":[65],"selecting":[66],"relatively":[68],"small":[69],"feature":[70,85],"set":[71,86],"in":[72,103],"just":[73],"couple":[75],"passes":[77],"over":[78],"training":[80,97],"data.":[81],"However,":[82],"using":[83],"(initialized":[92],"their":[94],"weights),":[95],"CRF":[96],"provides":[98],"an":[99],"additional":[100],"0.5%":[101],"reduction":[102,112],"word":[104],"error":[105],"rate,":[106],"total":[109],"1.8%":[110],"absolute":[111],"39.2%.":[117]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":16}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}