{"id":"https://openalex.org/W70399244","doi":null,"title":"Domain Adaptation of Rule-Based Annotators for Named-Entity Recognition Tasks","display_name":"Domain Adaptation of Rule-Based Annotators for Named-Entity Recognition Tasks","publication_year":2010,"publication_date":"2010-10-09","ids":{"openalex":"https://openalex.org/W70399244","mag":"70399244"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.173.697","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.173.697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ucsc.edu/%7Elaura/papers/2010/emnlp2010.pdf","raw_type":"text"},"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/A5050310059","display_name":"Laura Chiticariu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Chiticariu","raw_affiliation_strings":["IBM Research -- Almaden, San Jose, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research -- Almaden, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rajasekar Krishnamurthy","orcid":"https://orcid.org/0000-0002-1245-4152","observed_orcids":["https://orcid.org/0000-0002-1245-4152"]},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajasekar Krishnamurthy","raw_affiliation_strings":["IBM Research -- Almaden, San Jose, CA"],"raw_orcid":"https://orcid.org/0000-0002-1245-4152","affiliations":[{"raw_affiliation_string":"IBM Research -- Almaden, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404797","display_name":"Yunyao Li","orcid":"https://orcid.org/0009-0003-9142-6890","observed_orcids":["https://orcid.org/0009-0003-9142-6890"]},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyao Li","raw_affiliation_strings":["IBM Research -- Almaden, San Jose, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research -- Almaden, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074416632","display_name":"Frederick R. Reiss","orcid":"https://orcid.org/0009-0002-1254-1798","observed_orcids":["https://orcid.org/0009-0002-1254-1798"]},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frederick Reiss","raw_affiliation_strings":["IBM Research -- Almaden, San Jose, CA"],"raw_orcid":"https://orcid.org/0009-0002-1254-1798","affiliations":[{"raw_affiliation_string":"IBM Research -- Almaden, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010223683","display_name":"Shivakumar Vaithyanathan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivakumar Vaithyanathan","raw_affiliation_strings":["IBM Research -- Almaden, San Jose, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research -- Almaden, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":11.1748,"has_fulltext":false,"cited_by_count":129,"citation_normalized_percentile":{"value":0.9863265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1002","last_page":"1012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9175000190734863,"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":0.9175000190734863,"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":0.06419999897480011,"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":0.003000000026077032,"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":0.9950000047683716},{"id":"https://openalex.org/keywords/rule-based-annotation","display_name":"rule-based annotation","score":0.7829999923706055},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.9549999833106995},{"id":"https://openalex.org/keywords/explainability","display_name":"explainability","score":0.9200000166893005},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.5170000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8773659467697144},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8331140279769897},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6044725775718689},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.602401077747345},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.59567791223526},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.5921968221664429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5901134014129639},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5646620988845825},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5371971726417542},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48643016815185547},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4808162450790405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4723808765411377},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4613412022590637},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14857926964759827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":"pmh:oai:CiteSeerX.psu:10.1.1.173.697","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.173.697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ucsc.edu/%7Elaura/papers/2010/emnlp2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.653","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology-new/D/D10/D10-1098.pdf","raw_type":"text"},{"id":"mag:70399244","doi":null,"is_oa":false,"landing_page_url":"http://researcher.watson.ibm.com/researcher/files/us-yunyaoli/emnlp2010-SystemT-namedEntity.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W10455613","https://openalex.org/W30446498","https://openalex.org/W1492228966","https://openalex.org/W1500614872","https://openalex.org/W1515435652","https://openalex.org/W1516748551","https://openalex.org/W1520377376","https://openalex.org/W1606142945","https://openalex.org/W1729904568","https://openalex.org/W1763847398","https://openalex.org/W1862498505","https://openalex.org/W1969595233","https://openalex.org/W1976339715","https://openalex.org/W1982626598","https://openalex.org/W1999563429","https://openalex.org/W2020278455","https://openalex.org/W2026147653","https://openalex.org/W2047477415","https://openalex.org/W2056354103","https://openalex.org/W2056451646","https://openalex.org/W2096259344","https://openalex.org/W2098720114","https://openalex.org/W2106950427","https://openalex.org/W2111069012","https://openalex.org/W2128313564","https://openalex.org/W2135352205","https://openalex.org/W2140988362","https://openalex.org/W2141099517","https://openalex.org/W2144416276","https://openalex.org/W2144578941","https://openalex.org/W2145386458","https://openalex.org/W2148540243","https://openalex.org/W2157758844","https://openalex.org/W2158108973","https://openalex.org/W2164949130","https://openalex.org/W2166709576","https://openalex.org/W2167541073","https://openalex.org/W2398591267"],"related_works":["https://openalex.org/W2146291263","https://openalex.org/W1967974418","https://openalex.org/W7095627321","https://openalex.org/W2138780451","https://openalex.org/W2243659261","https://openalex.org/W2512833950","https://openalex.org/W2342853654","https://openalex.org/W1530375956","https://openalex.org/W4239111889","https://openalex.org/W2792238823"],"abstract_inverted_index":{"Named-entity":[0],"recognition":[1],"(NER)":[2],"is":[3,83],"an":[4],"important":[5],"task":[6],"required":[7],"in":[8,49],"a":[9,56,68,76],"wide":[10],"variety":[11],"of":[12,74,88,95,131],"applications.":[13],"While":[14],"rule-based":[15,53,101,132,150],"systems":[16,54],"are":[17,33],"appealing":[18],"due":[19],"to":[20,59,85],"their":[21],"well-known":[22],"\u201cexplainability,\u201d":[23],"most,":[24],"if":[25],"not":[26],"all,":[27],"state-of-the-art":[28],"results":[29,116,123],"for":[30],"NER":[31,89],"tasks":[32,90],"based":[34],"on":[35,72],"machine":[36,119],"learning":[37,120],"techniques.":[38,121],"Motivated":[39],"by":[40,141],"these":[41,107],"results,":[42],"we":[43,63,126],"explore":[44],"the":[45,86,93,113,129],"following":[46],"natural":[47],"question":[48],"this":[50],"paper:":[51],"Are":[52],"still":[55],"viable":[57],"approach":[58],"named-entity":[60,102],"recognition?":[61],"Specifically,":[62],"have":[64],"designed":[65],"and":[66,91,98,147,152],"implemented":[67],"high-level":[69],"language":[70],"NERL":[71,82],"top":[73],"SystemT,":[75],"general-purpose":[77],"algebraic":[78],"information":[79],"extraction":[80],"system.":[81],"tuned":[84],"needs":[87],"simplifies":[92],"process":[94],"building,":[96],"understanding,":[97],"customizing":[99,148],"complex":[100,149],"annotators.":[103],"We":[104,139],"show":[105],"that":[106,125],"customized":[108],"annotators":[109,151],"match":[110],"or":[111],"outperform":[112],"best":[114],"published":[115],"achieved":[117],"with":[118],"These":[122],"confirm":[124],"can":[127],"reap":[128],"benefits":[130],"extractors":[133],"\u2019":[134],"explainability":[135],"without":[136],"sacrificing":[137],"accuracy.":[138],"conclude":[140],"discussing":[142],"lessons":[143],"learned":[144],"while":[145],"building":[146],"outlining":[153],"several":[154],"research":[155],"directions":[156],"towards":[157],"facilitating":[158],"rule":[159],"development.":[160],"1":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":11}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}