{"id":"https://openalex.org/W2130581319","doi":"https://doi.org/10.3115/1220175.1220234","title":"Improving the scalability of semi-Markov conditional random fields for named entity recognition","display_name":"Improving the scalability of semi-Markov conditional random fields for named entity recognition","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2130581319","doi":"https://doi.org/10.3115/1220175.1220234","mag":"2130581319"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220234","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220234","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","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/10.3115/1220175.1220234","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056883370","display_name":"Daisuke Okanohara","orcid":"https://orcid.org/0000-0001-5969-587X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Daisuke Okanohara","raw_affiliation_strings":["University of Tokyo, Bunkyo-ku, Tokyo, Japan","University of Tokyo Bunkyo-ku Tokyo Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Tokyo Bunkyo-ku Tokyo Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004444958","display_name":"Yusuke Miyao","orcid":"https://orcid.org/0000-0002-0678-3400"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Miyao","raw_affiliation_strings":["University of Tokyo, Bunkyo-ku, Tokyo, Japan","University of Tokyo Bunkyo-ku Tokyo Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Tokyo Bunkyo-ku Tokyo Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064113904","display_name":"Yoshimasa Tsuruoka","orcid":"https://orcid.org/0000-0002-0707-1077"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yoshimasa Tsuruoka","raw_affiliation_strings":["University of Manchester, Manchester, UK","University\u00a0of\u00a0Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"University\u00a0of\u00a0Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112241147","display_name":"Jun\u2019ichi Tsujii","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Jun'ichi Tsujii","raw_affiliation_strings":["University of Tokyo, Bunkyo-ku, Tokyo, Japan and University of Manchester, Manchester, UK and Solution Oriented Research for Science and Technology, Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Bunkyo-ku, Tokyo, Japan and University of Manchester, Manchester, UK and Solution Oriented Research for Science and Technology, Saitama, Japan","institution_ids":["https://openalex.org/I28407311","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056883370"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":13.0258,"has_fulltext":true,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98732598,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"465","last_page":"472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9921000003814697,"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":0.8389023542404175},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.7463524341583252},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6974077224731445},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6890432834625244},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6290598511695862},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6002025604248047},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5814527869224548},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5778236389160156},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5672573447227478},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.535494863986969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5105441808700562},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4583195745944977},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4406885802745819},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4112106263637543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40928974747657776},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36663514375686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389023542404175},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.7463524341583252},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6974077224731445},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6890432834625244},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6290598511695862},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6002025604248047},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5814527869224548},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5778236389160156},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5672573447227478},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.535494863986969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105441808700562},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4583195745944977},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4406885802745819},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4112106263637543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40928974747657776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36663514375686646},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1220175.1220234","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220234","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.8198","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.8198","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/P06/P06-1059.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.6665","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.6665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-tsujii.is.s.u-tokyo.ac.jp/~hillbig/papers/acl2006_semicrf.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220234","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220234","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2130581319.pdf","grobid_xml":"https://content.openalex.org/works/W2130581319.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1501508411","https://openalex.org/W1976574743","https://openalex.org/W1986372192","https://openalex.org/W2000363133","https://openalex.org/W2004111828","https://openalex.org/W2021331223","https://openalex.org/W2039612385","https://openalex.org/W2047782770","https://openalex.org/W2081850059","https://openalex.org/W2096765155","https://openalex.org/W2114361266","https://openalex.org/W2137650255","https://openalex.org/W2147880316","https://openalex.org/W2150722176","https://openalex.org/W2152455533","https://openalex.org/W2158188757","https://openalex.org/W2163918411","https://openalex.org/W2793249556","https://openalex.org/W4302585900"],"related_works":["https://openalex.org/W1964783010","https://openalex.org/W2962906565","https://openalex.org/W4250494529","https://openalex.org/W2399696375","https://openalex.org/W2798423868","https://openalex.org/W2061834489","https://openalex.org/W189110383","https://openalex.org/W2062502130","https://openalex.org/W2132038179","https://openalex.org/W2027233318"],"abstract_inverted_index":{"This":[0,79],"paper":[1],"presents":[2],"techniques":[3],"to":[4,7,57,83,108],"apply":[5],"semi-CRFs":[6],"Named":[8],"Entity":[9],"Recognition":[10],"tasks":[11],"with":[12],"a":[13,68,85,105],"tractable":[14],"computational":[15,35,40],"cost.":[16,36],"Our":[17],"framework":[18,80],"can":[19,96],"handle":[20],"an":[21,128],"NER":[22],"task":[23,137],"that":[24,95,124],"has":[25],"long":[26],"named":[27],"entities":[28,113],"and":[29,61],"many":[30],"labels":[31],"which":[32,54,71],"increase":[33],"the":[34,39,46,49,62,65,74,92,133],"To":[37],"reduce":[38],"cost,":[41],"we":[42],"propose":[43],"two":[44],"techniques:":[45],"first":[47],"is":[48,64],"use":[50,84],"of":[51,67,76,88,100,130],"feature":[52],"forests,":[53],"enables":[55],"us":[56,82],"pack":[58],"feature-equivalent":[59],"states,":[60],"second":[63],"introduction":[66],"filtering":[69],"process":[70],"significantly":[72],"reduces":[73],"number":[75],"candidate":[77],"states.":[78],"allows":[81],"rich":[86],"set":[87],"features":[89],"extracted":[90],"from":[91],"chunk-based":[93],"representation":[94],"capture":[97],"informative":[98],"characteristics":[99],"entities.":[101],"We":[102],"also":[103],"introduce":[104],"simple":[106],"trick":[107],"transfer":[109],"information":[110,117],"about":[111],"distant":[112],"by":[114],"embedding":[115],"label":[116],"into":[118],"non-entity":[119],"labels.":[120],"Experimental":[121],"results":[122],"show":[123],"our":[125],"model":[126],"achieves":[127],"F-score":[129],"71.48%":[131],"on":[132],"JNLPBA":[134],"2004":[135],"shared":[136],"without":[138],"using":[139],"any":[140],"external":[141],"resources":[142],"or":[143],"post-processing":[144],"techniques.":[145]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}