{"id":"https://openalex.org/W2585157431","doi":"https://doi.org/10.1109/bigdata.2016.7841065","title":"Lightweight system for NE-tagged news headlines corpus creation","display_name":"Lightweight system for NE-tagged news headlines corpus creation","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2585157431","doi":"https://doi.org/10.1109/bigdata.2016.7841065","mag":"2585157431"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7841065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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/A5105366572","display_name":"Avinash Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Avinash Kumar","raw_affiliation_strings":["Indian Institute of Technology, Roorkee, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033934770","display_name":"Dhaval Patel","orcid":"https://orcid.org/0000-0002-5449-6975"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhaval Patel","raw_affiliation_strings":["Indian Institute of Technology, Roorkee, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108133591","display_name":"Nikita Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nikita Jain","raw_affiliation_strings":["Indian Institute of Technology, Roorkee, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5105366572"],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10834844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3903","last_page":"3912"},"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9966999888420105,"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/hindi","display_name":"Hindi","score":0.9237273931503296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8603712320327759},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7454841136932373},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6421020030975342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6367643475532532},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5697289705276489},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5681612491607666},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4264673888683319},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09436807036399841}],"concepts":[{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.9237273931503296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603712320327759},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7454841136932373},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6421020030975342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367643475532532},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5697289705276489},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5681612491607666},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4264673888683319},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09436807036399841},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7841065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.5799999833106995,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W164249384","https://openalex.org/W785060174","https://openalex.org/W1846321791","https://openalex.org/W2035459359","https://openalex.org/W2096765155","https://openalex.org/W2104912629","https://openalex.org/W2144934730","https://openalex.org/W2251593985","https://openalex.org/W2252061787","https://openalex.org/W2756223574","https://openalex.org/W6606676582","https://openalex.org/W6675734994","https://openalex.org/W6691691090","https://openalex.org/W6691914234"],"related_works":["https://openalex.org/W2510663906","https://openalex.org/W2078793151","https://openalex.org/W3017222382","https://openalex.org/W3128216712","https://openalex.org/W3136915866","https://openalex.org/W2886890203","https://openalex.org/W4390279576","https://openalex.org/W4313535650","https://openalex.org/W2287770975","https://openalex.org/W2991463832"],"abstract_inverted_index":{"Named":[0],"Entity":[1],"Identification":[2],"(NEI)":[3],"is":[4,41,50],"the":[5,32,46,51,100,112,123],"task":[6],"of":[7,36,45,53,76,91,102,114],"identifying":[8],"named":[9,78],"entities":[10,79],"from":[11],"textual":[12],"data.":[13],"While":[14],"NEI":[15],"for":[16,48],"English":[17],"language":[18,128],"can":[19,64,132],"be":[20,65,134],"done":[21],"with":[22],"considerable":[23],"accuracy":[24,33],"owing":[25],"to":[26,84,105,111,126,136],"tools":[27],"like":[28,39],"Stanford":[29],"NER":[30],"tagger,":[31],"in":[34,58,80],"case":[35],"Indian":[37,59],"languages":[38,60,138],"Hindi":[40,81,127],"comparatively":[42],"poor.":[43],"One":[44],"reasons":[47],"this":[49,68],"lack":[52],"sufficiently":[54],"large":[55],"annotated":[56],"corpora":[57],"on":[61],"which":[62,144],"NE-taggers":[63,107],"trained.":[66],"In":[67],"paper,":[69],"we":[70,120],"describe":[71],"a":[72,86],"lightweight,":[73],"automated":[74],"process":[75,124],"tagging":[77],"news":[82,93],"headlines":[83],"create":[85],"huge":[87],"silver":[88],"standard":[89,116],"corpus":[90,104],"NE-tagged":[92],"headlines.":[94],"We":[95],"show,":[96],"via":[97],"experiments,":[98],"that":[99],"use":[101,113],"our":[103,130,148],"train":[106],"produces":[108],"comparable":[109],"results":[110],"gold":[115],"training":[117],"corpus.":[118],"Although":[119],"have":[121],"applied":[122,135],"majorly":[125],"only,":[129],"method":[131],"also":[133],"other":[137],"provided":[139],"they":[140],"fulfill":[141],"certain":[142],"requirements":[143],"are":[145],"necessitated":[146],"by":[147],"process.":[149]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}