{"id":"https://openalex.org/W2154547898","doi":"https://doi.org/10.1145/1772690.1772738","title":"A scalable machine-learning approach for semi-structured named entity recognition","display_name":"A scalable machine-learning approach for semi-structured named entity recognition","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W2154547898","doi":"https://doi.org/10.1145/1772690.1772738","mag":"2154547898"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772738","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5060202357","display_name":"Utku Irmak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Utku Irmak","raw_affiliation_strings":["Yahoo! Inc, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Inc, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039673620","display_name":"Reiner Kraft","orcid":"https://orcid.org/0000-0002-3794-668X"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reiner Kraft","raw_affiliation_strings":["Yahoo! Inc, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Inc, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060202357"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":3.2515,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92649582,"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":"461","last_page":"470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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":0.9995999932289124,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9986000061035156,"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":0.8494323492050171},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6790134906768799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6235698461532593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6190667748451233},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5576201677322388},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5381380915641785},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.5325426459312439},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4698202908039093},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4361693263053894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3757988512516022},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3748021125793457},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.22408562898635864},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10739687085151672},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10039710998535156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8494323492050171},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6790134906768799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6235698461532593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6190667748451233},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5576201677322388},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5381380915641785},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.5325426459312439},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4698202908039093},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4361693263053894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3757988512516022},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3748021125793457},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.22408562898635864},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10739687085151672},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10039710998535156},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":2,"locations":[{"id":"doi:10.1145/1772690.1772738","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.3667","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.3667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cis.poly.edu/%7Euirmak/publications/bootstrap.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W167355512","https://openalex.org/W197270748","https://openalex.org/W199174415","https://openalex.org/W1489949474","https://openalex.org/W1496059925","https://openalex.org/W1514997941","https://openalex.org/W1567365482","https://openalex.org/W1574901103","https://openalex.org/W1978394996","https://openalex.org/W1981537631","https://openalex.org/W2000586878","https://openalex.org/W2005909019","https://openalex.org/W2039150623","https://openalex.org/W2050078085","https://openalex.org/W2054092228","https://openalex.org/W2075635421","https://openalex.org/W2096186751","https://openalex.org/W2103931177","https://openalex.org/W2118585731","https://openalex.org/W2132870739","https://openalex.org/W2133108446","https://openalex.org/W2146427684","https://openalex.org/W2148540243","https://openalex.org/W2149469409","https://openalex.org/W2160987310","https://openalex.org/W2164949130","https://openalex.org/W2166776180","https://openalex.org/W2169307587","https://openalex.org/W2785349534","https://openalex.org/W2917460666","https://openalex.org/W3001645704","https://openalex.org/W6629296869"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W2155874911","https://openalex.org/W3000685722","https://openalex.org/W4255258373","https://openalex.org/W2032007337","https://openalex.org/W1884363728","https://openalex.org/W4253099099","https://openalex.org/W4386977977","https://openalex.org/W4313162113","https://openalex.org/W3198729192"],"abstract_inverted_index":{"Named":[0],"entity":[1,117],"recognition":[2],"studies":[3],"the":[4,26],"problem":[5],"of":[6,11,17,28,39,58,88,100],"locating":[7],"and":[8,31,46,91,122],"classifying":[9],"parts":[10],"free":[12],"text":[13],"into":[14],"a":[15,50],"set":[16],"predefined":[18],"categories.":[19],"Although":[20],"extensive":[21],"research":[22],"has":[23],"focused":[24],"on":[25,97],"detection":[27],"person,":[29],"location":[30],"organization":[32],"entities,":[33],"there":[34],"are":[35],"many":[36,115,120],"other":[37],"entities":[38,59],"interest,":[40],"including":[41],"phone":[42],"numbers,":[43],"dates,":[44],"times":[45],"currencies":[47],"(to":[48],"name":[49],"few":[51],"examples).":[52],"We":[53],"refer":[54],"to":[55,72,113],"these":[56,105],"types":[57,118],"as":[60],"\"semi-structured":[61],"named":[62],"entities\",":[63],"since":[64],"they":[65],"usually":[66],"follow":[67],"certain":[68],"syntactic":[69],"formats":[70],"according":[71],"some":[73],"conventions,":[74],"although":[75],"their":[76],"structure":[77],"is":[78],"typically":[79],"not":[80,108],"well-defined.":[81],"Regular":[82],"expression":[83],"solutions":[84],"require":[85],"significant":[86],"amount":[87],"manual":[89],"effort":[90],"supervised":[92],"machine":[93],"learning":[94],"approaches":[95,106],"rely":[96],"large":[98],"sets":[99],"labeled":[101],"training":[102],"data.":[103],"Therefore,":[104],"do":[107],"scale":[109],"when":[110],"we":[111],"need":[112],"support":[114],"semi-structured":[116],"in":[119],"languages":[121],"regions.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}