{"id":"https://openalex.org/W1760653846","doi":"https://doi.org/10.17562/pb-38-4","title":"Named Entity Recognition in Hindi using Maximum Entropy and Transliteration","display_name":"Named Entity Recognition in Hindi using Maximum Entropy and Transliteration","publication_year":2008,"publication_date":"2008-12-31","ids":{"openalex":"https://openalex.org/W1760653846","doi":"https://doi.org/10.17562/pb-38-4","mag":"1760653846"},"language":"en","primary_location":{"id":"doi:10.17562/pb-38-4","is_oa":false,"landing_page_url":"https://doi.org/10.17562/pb-38-4","pdf_url":null,"source":{"id":"https://openalex.org/S4210186437","display_name":"Polibits","issn_l":"1870-9044","issn":["1870-9044","2395-8618"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Polibits","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/A5015406724","display_name":"Sujan Kumar Saha","orcid":"https://orcid.org/0000-0002-7275-7980"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sujan Kumar Saha","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001735719","display_name":"Partha Ghosh","orcid":"https://orcid.org/0000-0003-4808-3370"},"institutions":[{"id":"https://openalex.org/I96211989","display_name":"HCL Technologies (India)","ror":"https://ror.org/02nbb5780","country_code":"IN","type":"company","lineage":["https://openalex.org/I96211989"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Partha Sarathi Ghosh","raw_affiliation_strings":["HCL Technologies, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HCL Technologies, Bangalore, India","institution_ids":["https://openalex.org/I96211989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024219981","display_name":"Sudeshna Sarkar","orcid":"https://orcid.org/0000-0003-3439-4282"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudeshna Sarkar","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032809289","display_name":"Pabitra Mitra","orcid":"https://orcid.org/0000-0002-1908-9813"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pabitra Mitra","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5837,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.7705535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"38","issue":null,"first_page":"33","last_page":"41"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9945999979972839,"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/transliteration","display_name":"Transliteration","score":0.8029561042785645},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.7060299515724182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6075847148895264},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5664909482002258},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5240254998207092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47932326793670654},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39970386028289795}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8029561042785645},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.7060299515724182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6075847148895264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5664909482002258},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5240254998207092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47932326793670654},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39970386028289795}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.17562/pb-38-4","is_oa":false,"landing_page_url":"https://doi.org/10.17562/pb-38-4","pdf_url":null,"source":{"id":"https://openalex.org/S4210186437","display_name":"Polibits","issn_l":"1870-9044","issn":["1870-9044","2395-8618"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Polibits","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.4960","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.4960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gelbukh.com/polibits/38_04.pdf","raw_type":"text"},{"id":"pmh:oai:redalyc.org:402640451004","is_oa":false,"landing_page_url":"https://www.redalyc.org/articulo.oa?id=402640451004","pdf_url":null,"source":{"id":"https://openalex.org/S4377196100","display_name":"Redalyc (Universidad Aut\u00f3noma del Estado de M\u00e9xico)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I179647637","host_organization_name":"Universidad Aut\u00f3noma del Estado de M\u00e9xico","host_organization_lineage":["https://openalex.org/I179647637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Polibits (M\u00e9xico) Vol.38","raw_type":"art\u00edculo cient\u00edfico"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W14030242","https://openalex.org/W1505083828","https://openalex.org/W1941319617","https://openalex.org/W1995287322","https://openalex.org/W2019614587","https://openalex.org/W2026147653","https://openalex.org/W2067326963","https://openalex.org/W2090362702","https://openalex.org/W2132903501","https://openalex.org/W2138871615","https://openalex.org/W2160842254","https://openalex.org/W2163918411","https://openalex.org/W2786972369","https://openalex.org/W2913739034","https://openalex.org/W3198132752","https://openalex.org/W3198534939"],"related_works":["https://openalex.org/W2147866274","https://openalex.org/W2350015575","https://openalex.org/W2371976984","https://openalex.org/W2352160949","https://openalex.org/W2378436233","https://openalex.org/W2096393573","https://openalex.org/W190438618","https://openalex.org/W4385625167","https://openalex.org/W2069398544","https://openalex.org/W2018369711"],"abstract_inverted_index":{"Abstract\u2014Named":[0],"entities":[1],"are":[2,33,38,56,63,124,130],"perhaps":[3],"the":[4,14,42,70,75,102,113,117,120,127,140,161,167,188],"most":[5,12],"important":[6],"indexing":[7],"element":[8],"in":[9,65,74,112,131,139,166,191],"text":[10],"for":[11,41,78,93,101,179],"of":[13,21,44,53,119,154],"information":[15],"extraction":[16],"and":[17,129,195],"mining":[18],"tasks.":[19],"Construction":[20],"a":[22,87,147],"Named":[23],"Entity":[24],"Recognition":[25],"(NER)":[26],"system":[27,92,114],"becomes":[28],"challenging":[29],"if":[30],"proper":[31,54],"resources":[32],"not":[34,57],"available.":[35],"Gazetteer":[36],"lists":[37,52,62,72,111,123,137,165],"often":[39],"used":[40],"development":[43],"NER":[45,76,91,104,142,193],"systems.":[46],"In":[47,81],"many":[48],"resource-poor":[49],"languages":[50],"gazetteer":[51,110,164,173],"size":[55],"available,":[58],"but":[59],"sometimes":[60],"relevant":[61],"available":[64],"English.":[66,132],"Proper":[67],"transliteration":[68,149,162,171,189],"makes":[69],"English":[71,136],"useful":[73,138],"tasks":[77],"such":[79],"languages.":[80,181],"this":[82],"paper,":[83],"we":[84,144,185],"have":[85,96,107,145,186],"described":[86],"Maximum":[88],"Entropy":[89],"based":[90,163,172],"Hindi.":[94],"We":[95,106],"explored":[97],"different":[98],"features":[99],"applicable":[100,178],"Hindi":[103,141],"task.":[105],"incorporated":[108],"some":[109],"to":[115],"increase":[116],"performance":[118,155,198],"system.":[121,168],"These":[122],"collected":[125],"from":[126,183],"web":[128],"To":[133],"make":[134],"these":[135],"task,":[143],"proposed":[146,170],"two-phase":[148],"methodology.":[150],"A":[151],"considerable":[152],"amount":[153],"improvement":[156],"is":[157,176],"observed":[158],"after":[159],"using":[160],"The":[169],"preparation":[174],"methodology":[175],"also":[177,196],"other":[180],"Apart":[182],"Hindi,":[184],"applied":[187],"approach":[190],"Bengali":[192],"task":[194],"achieved":[197],"improvement.":[199],"Index":[200],"Terms\u2014Gazetteer":[201],"list":[202],"preparation,":[203],"named":[204],"entity":[205],"recognition,":[206],"natural":[207],"language":[208],"processing,":[209],"transliteration.":[210],"N":[211],"I.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}