{"id":"https://openalex.org/W2572043993","doi":"https://doi.org/10.1145/3015467","title":"Named Entity Recognition with Word Embeddings and Wikipedia Categories for a Low-Resource Language","display_name":"Named Entity Recognition with Word Embeddings and Wikipedia Categories for a Low-Resource Language","publication_year":2017,"publication_date":"2017-01-20","ids":{"openalex":"https://openalex.org/W2572043993","doi":"https://doi.org/10.1145/3015467","mag":"2572043993"},"language":"en","primary_location":{"id":"doi:10.1145/3015467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3015467","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5005095321","display_name":"Arjun Das","orcid":null},"institutions":[{"id":"https://openalex.org/I106542073","display_name":"University of Calcutta","ror":"https://ror.org/01e7v7w47","country_code":"IN","type":"education","lineage":["https://openalex.org/I106542073"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arjun Das","raw_affiliation_strings":["University of Calcutta, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Calcutta, Kolkata, India","institution_ids":["https://openalex.org/I106542073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082339849","display_name":"Debasis Ganguly","orcid":"https://orcid.org/0000-0003-0050-7138"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Debasis Ganguly","raw_affiliation_strings":["Dublin City University, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024170958","display_name":"Utpal Garain","orcid":"https://orcid.org/0000-0001-7207-5018"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Utpal Garain","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7851,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.95896473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9947999715805054,"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":0.7695703506469727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7386164665222168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7357869744300842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6505420804023743},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6427112817764282},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5968751907348633},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4981379508972168},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4906095564365387},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.48247459530830383},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.4758074879646301},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.44625550508499146},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4130079746246338},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3682830333709717},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3409234881401062},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.31191033124923706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18321016430854797}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7695703506469727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386164665222168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7357869744300842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6505420804023743},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6427112817764282},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5968751907348633},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4981379508972168},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4906095564365387},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.48247459530830383},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.4758074879646301},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.44625550508499146},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4130079746246338},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3682830333709717},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3409234881401062},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31191033124923706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18321016430854797},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3015467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3015467","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1502473750","https://openalex.org/W1505083828","https://openalex.org/W1520377376","https://openalex.org/W1527478795","https://openalex.org/W1982982698","https://openalex.org/W1997157351","https://openalex.org/W2004763266","https://openalex.org/W2042262817","https://openalex.org/W2051791742","https://openalex.org/W2072916690","https://openalex.org/W2075783691","https://openalex.org/W2097147084","https://openalex.org/W2099253769","https://openalex.org/W2106525823","https://openalex.org/W2117130368","https://openalex.org/W2120120683","https://openalex.org/W2123512824","https://openalex.org/W2131462252","https://openalex.org/W2131571251","https://openalex.org/W2136364310","https://openalex.org/W2140701953","https://openalex.org/W2141099517","https://openalex.org/W2156488976","https://openalex.org/W2156515921","https://openalex.org/W2157807817","https://openalex.org/W2158899491","https://openalex.org/W2187089797","https://openalex.org/W2251680502","https://openalex.org/W2251874673","https://openalex.org/W2305500718","https://openalex.org/W2610593052","https://openalex.org/W2618735189","https://openalex.org/W2911964244","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2964266863","https://openalex.org/W2998768810","https://openalex.org/W3088104242"],"related_works":["https://openalex.org/W4250494529","https://openalex.org/W2403176590","https://openalex.org/W1964783010","https://openalex.org/W2399696375","https://openalex.org/W45206245","https://openalex.org/W2211396092","https://openalex.org/W4305041692","https://openalex.org/W2078793151","https://openalex.org/W2061834489","https://openalex.org/W2751906762"],"abstract_inverted_index":{"In":[0,53,247],"this":[1,105],"article,":[2],"we":[3,56,110,165,207,267],"propose":[4,166,208],"a":[5,18,87,112,123,136,188,202,205,235],"word":[6,77,157,192],"embedding--based":[7],"named":[8,175],"entity":[9,176],"recognition":[10],"(NER)":[11],"approach.":[12],"NER":[13,71,128,131,245,280],"is":[14,75,108],"commonly":[15],"approached":[16],"as":[17,28,47,86],"sequence":[19],"labeling":[20],"task":[21,282],"with":[22,230,291],"the":[23,38,60,63,70,81,95,100,117,127,182,191,213,217,224,243,255,273,277,294],"application":[24],"of":[25,40,59,62,66,99,119,156,184,212,220,226,262,288],"methods":[26,45],"such":[27,46,85],"conditional":[29],"random":[30],"field":[31],"(CRF).":[32],"However,":[33],"for":[34,276],"low-resource":[35,140,189],"languages":[36],"without":[37],"presence":[39],"sufficiently":[41],"large":[42],"training":[43,185,228],"data,":[44],"CRF":[48,150],"do":[49],"not":[50,198],"perform":[51],"well.":[52],"our":[54,249,269],"work,":[55],"make":[57,210],"use":[58,153,211],"proximity":[61],"vector":[64,97,218],"embeddings":[65,158,219],"words":[67,120,221],"to":[68,80,121,200,209,222,272,293],"approach":[69,115,145,169,259,271],"problem.":[72],"The":[73],"hypothesis":[74,107],"that":[76,104,152,238],"vectors":[78,118,193],"belonging":[79],"same":[82],"name":[83],"category,":[84],"person\u2019s":[88],"name,":[89],"occur":[90],"in":[91,94,181,242],"close":[92],"vicinity":[93],"abstract":[96],"space":[98],"embedded":[101],"words.":[102],"Assuming":[103],"clustering":[106],"true,":[109],"apply":[111],"standard":[113,148],"classification":[114],"on":[116,135],"learn":[122],"decision":[124],"boundary":[125],"between":[126,216],"classes.":[129],"Our":[130,144],"experiments":[132],"are":[133,197],"conducted":[134],"morphologically":[137],"rich":[138],"and":[139,159,283],"language,":[141,190],"namely":[142],"Bengali.":[143],"significantly":[146],"outperforms":[147],"baseline":[149],"approaches":[151],"cluster":[154],"labels":[155],"gazetteers":[160],"constructed":[161],"from":[162,179,195,234],"Wikipedia.":[163],"Further,":[164],"an":[167,172,285],"unsupervised":[168,244],"(that":[170],"uses":[171],"automatically":[173],"created":[174],"(NE)":[177],"gazetteer":[178],"Wikipedia":[180,196,227],"absence":[183],"data).":[186],"For":[187],"obtained":[194],"sufficient":[199],"train":[201],"classifier.":[203],"As":[204],"result,":[206],"distance":[214],"measure":[215],"expand":[223],"set":[225],"examples":[229],"additional":[231],"NEs":[232],"extracted":[233],"monolingual":[236],"corpus":[237],"yield":[239],"significant":[240],"improvement":[241,287],"performance.":[246],"fact,":[248],"expansion":[250],"method":[251],"performs":[252],"better":[253],"than":[254],"traditional":[256],"CRF-based":[257],"(supervised)":[258],"(i.e.,":[260],"F-score":[261,289],"65.4%":[263],"vs.":[264],"64.2%).":[265],"Finally,":[266],"compare":[268],"proposed":[270],"official":[274,296],"submission":[275],"IJCNLP-2008":[278],"Bengali":[279],"shared":[281],"achieve":[284],"overall":[286],"11.26%":[290],"respect":[292],"best":[295],"system.":[297]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}