{"id":"https://openalex.org/W1755456395","doi":"https://doi.org/10.3115/v1/e14-1048","title":"Learning Dictionaries for Named Entity Recognition using Minimal Supervision","display_name":"Learning Dictionaries for Named Entity Recognition using Minimal Supervision","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1755456395","doi":"https://doi.org/10.3115/v1/e14-1048","mag":"1755456395"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-1048","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/e14-1048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1504.06650","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043840749","display_name":"Arvind Neelakantan","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arvind Neelakantan","raw_affiliation_strings":["University of Massachusetts: Amherst#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079061237","display_name":"Michael Collins","orcid":"https://orcid.org/0000-0003-0997-1527"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Collins","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043840749"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":2.546,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90569646,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"452","last_page":"461"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9970999956130981,"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/phrase","display_name":"Phrase","score":0.8297908306121826},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7982380390167236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7410792112350464},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6982966661453247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6590927839279175},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6074053049087524},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.497346431016922},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4186776578426361},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36704957485198975},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34402602910995483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16093263030052185}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8297908306121826},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7982380390167236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410792112350464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6982966661453247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6590927839279175},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6074053049087524},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.497346431016922},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4186776578426361},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36704957485198975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34402602910995483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16093263030052185},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3115/v1/e14-1048","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/e14-1048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1504.06650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1504.06650","pdf_url":"https://arxiv.org/pdf/1504.06650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:1755456395","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1504.06650.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.683.8575","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.683.8575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://people.cs.umass.edu/%7Earvind/eacl_final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.882.5461","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.882.5461","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/E/E14/E14-1048.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1504.06650","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1504.06650","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1504.06650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1504.06650","pdf_url":"https://arxiv.org/pdf/1504.06650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W71154278","https://openalex.org/W98563929","https://openalex.org/W1536675765","https://openalex.org/W2004763266","https://openalex.org/W2048468185","https://openalex.org/W2048679005","https://openalex.org/W2091812280","https://openalex.org/W2114361266","https://openalex.org/W2117130368","https://openalex.org/W2117756735","https://openalex.org/W2129625650","https://openalex.org/W2141099517","https://openalex.org/W2151296343","https://openalex.org/W2950171587","https://openalex.org/W3088104242"],"related_works":["https://openalex.org/W2962776108","https://openalex.org/W1570587036","https://openalex.org/W2572043993","https://openalex.org/W2621151902","https://openalex.org/W2962802054","https://openalex.org/W3031118452","https://openalex.org/W2576091653","https://openalex.org/W1951325712","https://openalex.org/W3101231927","https://openalex.org/W605621","https://openalex.org/W2087923637","https://openalex.org/W3176489198","https://openalex.org/W2734693922","https://openalex.org/W2825128598","https://openalex.org/W3120861396","https://openalex.org/W2884915013","https://openalex.org/W2103316358","https://openalex.org/W2756894272","https://openalex.org/W2972157485","https://openalex.org/W2940614627"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"approach":[4],"for":[5,10,38],"automatic":[6],"construction":[7],"of":[8,18,49],"dictionaries":[9],"Named":[11],"Entity":[12],"Recognition":[13],"(NER)":[14],"using":[15,45,89],"large":[16],"amounts":[17],"unlabeled":[19],"data":[20],"and":[21,41,56,65],"a":[22,46,81],"few":[23],"seed":[24],"examples.":[25,51],"We":[26,69],"use":[27],"Canonical":[28],"Correlation":[29],"Analysis":[30],"(CCA)":[31],"to":[32,88],"obtain":[33],"lower":[34],"dimensional":[35],"embeddings":[36,77],"(representations)":[37],"candidate":[39,75],"phrases":[40,44],"classify":[42],"these":[43],"small":[47],"number":[48],"labeled":[50],"Our":[52],"method":[53],"achieves":[54],"16.5%":[55],"11.3%":[57],"F-1":[58],"score":[59],"improvement":[60],"over":[61],"co-training":[62],"on":[63],"disease":[64],"virus":[66],"NER":[67],"respectively.":[68],"also":[70],"show":[71],"that":[72],"by":[73],"adding":[74],"phrase":[76],"as":[78],"features":[79],"in":[80],"sequence":[82],"tagger":[83],"gives":[84],"better":[85],"performance":[86],"compared":[87],"word":[90],"embeddings.":[91]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}