{"id":"https://openalex.org/W64389275","doi":null,"title":"Exploiting domain and task regularities for robust named entity recognition","display_name":"Exploiting domain and task regularities for robust named entity recognition","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W64389275","mag":"64389275"},"language":"en","primary_location":{"id":"mag:64389275","doi":null,"is_oa":false,"landing_page_url":"http://reports-archive.adm.cs.cmu.edu/anon/ml2009/CMU-ML-09-109.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051617344","display_name":"William W. Cohen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William W. Cohen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010148946","display_name":"Andrew O. Arnold","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew O. Arnold","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.6607,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73610565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5220000147819519,"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":0.5220000147819519,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.18359999358654022,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.14589999616146088,"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/named-entity-recognition","display_name":"named entity recognition","score":0.9700000286102295},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.6439999938011169},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9179999828338623},{"id":"https://openalex.org/keywords/biological-text-mining","display_name":"biological text mining","score":0.6330000162124634},{"id":"https://openalex.org/keywords/feature-hierarchy","display_name":"feature hierarchy","score":0.925000011920929},{"id":"https://openalex.org/keywords/excerpts","display_name":"excerpts","score":0.6190000176429749},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458986639976501},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6206240653991699},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5989354848861694},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5887454748153687},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5629405975341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546054244041443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5098882913589478},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4786014258861542},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.46692487597465515},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.43276020884513855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1141575276851654},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":1,"locations":[{"id":"mag:64389275","doi":null,"is_oa":false,"landing_page_url":"http://reports-archive.adm.cs.cmu.edu/anon/ml2009/CMU-ML-09-109.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W60337842","https://openalex.org/W71647219","https://openalex.org/W202303397","https://openalex.org/W204184694","https://openalex.org/W317108637","https://openalex.org/W1482328859","https://openalex.org/W1510579866","https://openalex.org/W1532470117","https://openalex.org/W1534979469","https://openalex.org/W1540550673","https://openalex.org/W1550206324","https://openalex.org/W1559269947","https://openalex.org/W1568620938","https://openalex.org/W1571969069","https://openalex.org/W1592796124","https://openalex.org/W1597032530","https://openalex.org/W1630959083","https://openalex.org/W1760863262","https://openalex.org/W1866403196","https://openalex.org/W1966553486","https://openalex.org/W1968004512","https://openalex.org/W1979495886","https://openalex.org/W1982626598","https://openalex.org/W1994913251","https://openalex.org/W1996739860","https://openalex.org/W1998839399","https://openalex.org/W2022775778","https://openalex.org/W2048679005","https://openalex.org/W2049633694","https://openalex.org/W2056354103","https://openalex.org/W2058856481","https://openalex.org/W2063978378","https://openalex.org/W2064153289","https://openalex.org/W2068210077","https://openalex.org/W2079724595","https://openalex.org/W2091568528","https://openalex.org/W2096175520","https://openalex.org/W2096259344","https://openalex.org/W2097089247","https://openalex.org/W2101210369","https://openalex.org/W2101599977","https://openalex.org/W2102419107","https://openalex.org/W2103017472","https://openalex.org/W2104936489","https://openalex.org/W2107008379","https://openalex.org/W2107747058","https://openalex.org/W2108346334","https://openalex.org/W2111557120","https://openalex.org/W2113920009","https://openalex.org/W2114296159","https://openalex.org/W2118029084","https://openalex.org/W2120354757","https://openalex.org/W2120708938","https://openalex.org/W2129620481","https://openalex.org/W2130903752","https://openalex.org/W2131953535","https://openalex.org/W2133013156","https://openalex.org/W2133532371","https://openalex.org/W2134125014","https://openalex.org/W2135046866","https://openalex.org/W2135352205","https://openalex.org/W2136504847","https://openalex.org/W2136979193","https://openalex.org/W2138621811","https://openalex.org/W2143419558","https://openalex.org/W2145677303","https://openalex.org/W2147880316","https://openalex.org/W2148029428","https://openalex.org/W2148603752","https://openalex.org/W2152455533","https://openalex.org/W2157110051","https://openalex.org/W2158108973","https://openalex.org/W2159882563","https://openalex.org/W2162461580","https://openalex.org/W2163828439","https://openalex.org/W2166096645","https://openalex.org/W2166474856","https://openalex.org/W2167044614","https://openalex.org/W2168905447","https://openalex.org/W2169591950","https://openalex.org/W2293363371","https://openalex.org/W2293576742","https://openalex.org/W2420733993","https://openalex.org/W2785349534","https://openalex.org/W2913340405","https://openalex.org/W2964041960","https://openalex.org/W3099514962","https://openalex.org/W3151309449"],"related_works":["https://openalex.org/W2902824568","https://openalex.org/W2547450774","https://openalex.org/W2096259344","https://openalex.org/W2135352205","https://openalex.org/W4308599773","https://openalex.org/W3107540134","https://openalex.org/W3159500995","https://openalex.org/W3149011051","https://openalex.org/W2102419107","https://openalex.org/W7096692245"],"abstract_inverted_index":{"It":[0],"is":[1,82,106,119,374],"often":[2,19],"convenient":[3],"to":[4,84,143,173,203,209,219,226,275,348,367,376,396],"make":[5],"certain":[6],"assumptions":[7,17,24,140,161,191],"during":[8],"the":[9,23,47,74,78,87,94,112,153,212,236,257,292,295,299,312,315,358,362,399],"learning":[10,76,118,126,176,238],"process.":[11],"Unfortunately,":[12],"algorithms":[13],"built":[14],"on":[15,211,256,291],"these":[16,57,189],"can":[18,35,63,129,163,391],"break":[20],"down":[21],"if":[22],"are":[25,141,346],"not":[26,310],"stable":[27,419],"between":[28,86,111,352,398,424],"train":[29,102,113,400],"and":[30,89,96,103,114,137,149,157,165,169,206,222,252,298,364,389,401,409,414,416,421],"test":[31,90,104,115,402],"data.":[32,429],"Relatedly,":[33],"we":[34,62,124,146,155,162,194,242,384],"do":[36],"better":[37,217],"at":[38],"various":[39],"tasks":[40],"(like":[41],"named":[42,249],"entity":[43,250],"recognition)":[44],"by":[45,311,321,404,417],"exploiting":[46,56,418],"richer":[48],"relationships":[49,366,423],"found":[50],"in":[51,133,152,235,264,361],"real-world":[52],"complex":[53,422],"systems.":[54],"By":[55],"kinds":[58],"of":[59,80,188,260,294,301,314,427],"non-conventional":[60],"regularities":[61,151,380,420],"more":[64,197,394],"easily":[65],"address":[66],"problems":[67,154,229],"previously":[68,230],"unapproachable,":[69],"like":[70],"transfer":[71,75,237],"learning.":[72],"In":[73],"setting,":[77],"distribution":[79,300,313],"data":[81,296,309,325,363,403,406],"allowed":[83,142],"vary":[85],"training":[88],"domains,":[91],"that":[92,128,193,304,326,339,386,428],"is,":[93],"independent":[95],"identically":[97],"distributed":[98],"(i.i.d.)":[99],"assumption":[100],"linking":[101],"examples":[105],"severed.":[107],"Without":[108],"this":[109,122],"link":[110,308],"data,":[116,202],"traditional":[117],"difficult.":[120],"\r\nIn":[121,240],"thesis":[123],"explore":[125],"techniques":[127,245],"still":[130,170],"succeed":[131],"even":[132,223],"situations":[134],"where":[135],"i.i.d.":[136],"other":[138,207,369],"common":[139],"fail.":[144],"Specifically,":[145],"seek":[147],"out":[148],"exploit":[150,287],"encounter":[156],"document":[158],"which":[159,373],"specific":[160],"drop":[164],"under":[166],"what":[167],"circumstances":[168],"be":[171,334,392],"able":[172,225],"complete":[174],"our":[175],"task.":[177],"We":[178],"further":[179],"investigate":[180],"different":[181,328,425],"methods":[182],"for":[183,246,350],"dropping,":[184],"or":[185,317],"relaxing,":[186],"some":[187],"restrictive":[190],"so":[192],"may":[195],"bring":[196],"resources":[198],"(from":[199],"unlabeled":[200],"auxiliary":[201],"known":[204],"dependencies":[205],"regularities)":[208],"bear":[210],"problem,":[213],"thus":[214],"producing":[215,247],"both":[216],"answers":[218],"existing":[220],"problems,":[221],"being":[224],"begin":[227],"addressing":[228],"unanswerable,":[231],"such":[232],"as":[233,370],"those":[234],"setting.":[239],"particular,":[241],"introduce":[243],"four":[244],"robust":[248,379,395],"recognizers,":[251],"demonstrate":[253],"their":[254,318,322,365],"performance":[255],"problem":[258],"domain":[259],"protein":[261],"name":[262],"extraction":[263],"biological":[265],"publications:":[266],"(1)":[267],"Feature":[268],"hierarchies":[269],"relate":[270],"distinct,":[271],"though":[272],"related,":[273],"features":[274,286],"one":[276],"another":[277],"via":[278],"a":[279,288,371],"natural":[280],"linguistically-inspired":[281],"hierarchy.":[282],"(2)":[283],"Structural":[284],"frequency":[285],"regularity":[289],"based":[290],"structure":[293],"itself":[297],"instances":[302,316,338],"across":[303,381],"structure.":[305],"(3)":[306],"Snippets":[307],"features,":[319,342],"but":[320,330,343],"labels.":[323],"Thus":[324,383],"have":[327,340],"attributes,":[329],"similar":[331,341],"labels,":[332,345],"will":[333],"joined":[335],"together,":[336],"while":[337],"distinct":[344],"segregated":[347],"allow":[349],"variation":[351],"domains.":[353,382],"(4)":[354],"Graph":[355],"relations":[356],"represent":[357],"entities":[359],"contained":[360],"each":[368],"network":[372],"exploited":[375],"help":[377],"discover":[378],"show":[385],"learned":[387],"classifiers":[388],"extractors":[390],"made":[393],"shifts":[397],"using":[405],"(both":[407],"labeled":[408],"unlabeled)":[410],"from":[411],"related":[412],"domains":[413],"tasks,":[415],"aspects":[426]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2016-06-24T00:00:00"}