{"id":"https://openalex.org/W2904986391","doi":"https://doi.org/10.1109/kse.2018.8573411","title":"Building a Named Entity Annotated Bilingual English-Vietnamese Corpus","display_name":"Building a Named Entity Annotated Bilingual English-Vietnamese Corpus","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2904986391","doi":"https://doi.org/10.1109/kse.2018.8573411","mag":"2904986391"},"language":"en","primary_location":{"id":"doi:10.1109/kse.2018.8573411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2018.8573411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 10th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059152364","display_name":"An Dao","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tuan-An Dao","raw_affiliation_strings":["Faculty of Information Technology, University of Science - VNU.HCMC, HoChiMinh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Science - VNU.HCMC, HoChiMinh City, Vietnam","institution_ids":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009822967","display_name":"Thinh Hung Truong","orcid":"https://orcid.org/0000-0002-5242-4927"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hung-Thinh Truong","raw_affiliation_strings":["Faculty of Information Technology, University of Science - VNU.HCMC, HoChiMinh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Science - VNU.HCMC, HoChiMinh City, Vietnam","institution_ids":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048517713","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0002-0884-1635"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Long Nguyen","raw_affiliation_strings":["Faculty of Information Technology, University of Science - VNU.HCMC, HoChiMinh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Science - VNU.HCMC, HoChiMinh City, Vietnam","institution_ids":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040236875","display_name":"\u0110i\u1ec1n \u0110inh","orcid":"https://orcid.org/0000-0003-2069-1016"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dien Dinh","raw_affiliation_strings":["Faculty of Information Technology, University of Science - VNU.HCMC, HoChiMinh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Science - VNU.HCMC, HoChiMinh City, Vietnam","institution_ids":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":null,"first_page":"61","last_page":"66"},"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":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8813029527664185},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.8327109813690186},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7867782115936279},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7156858444213867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.705256998538971},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6275417804718018},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5945429801940918},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5384940505027771},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5365917682647705},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5350379347801208},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5224579572677612},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5087478756904602},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.45231786370277405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1200752854347229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8813029527664185},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8327109813690186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7867782115936279},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7156858444213867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.705256998538971},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6275417804718018},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5945429801940918},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5384940505027771},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5365917682647705},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5350379347801208},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5224579572677612},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5087478756904602},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.45231786370277405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1200752854347229},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kse.2018.8573411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2018.8573411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 10th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W42531066","https://openalex.org/W1977671488","https://openalex.org/W1991635536","https://openalex.org/W2006969979","https://openalex.org/W2016630033","https://openalex.org/W2123442489","https://openalex.org/W2133203418","https://openalex.org/W2251329024","https://openalex.org/W2251348249","https://openalex.org/W2251435463","https://openalex.org/W2531841301","https://openalex.org/W3140075257","https://openalex.org/W6652311901","https://openalex.org/W6691235938"],"related_works":["https://openalex.org/W4250494529","https://openalex.org/W1964783010","https://openalex.org/W2399696375","https://openalex.org/W45206245","https://openalex.org/W2211396092","https://openalex.org/W4305041692","https://openalex.org/W136407171","https://openalex.org/W3201257042","https://openalex.org/W2757016069","https://openalex.org/W3216421539"],"abstract_inverted_index":{"Bilingual":[0],"corpora":[1,25,118],"play":[2],"an":[3],"essential":[4],"role":[5],"in":[6,80,100,119],"Cross-lingual":[7],"Natural":[8],"Language":[9],"Processing":[10],"tasks":[11],"such":[12,24],"as":[13],"Machine":[14],"Translation,":[15],"Information":[16,19],"Extraction,":[17],"and":[18,29,67],"Retrieval.":[20],"Nevertheless,":[21],"manually":[22],"building":[23],"is":[26],"a":[27,43,52],"time-consuming":[28],"expensive":[30],"task,":[31],"especially":[32],"for":[33,64,70],"resource-limited":[34,121],"languages":[35],"like":[36],"Vietnamese.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"symmetric":[44],"Named":[45,82,93],"Entity":[46,83,94],"Alignment":[47],"method":[48,79,112],"to":[49,89,105,116],"automatically":[50],"construct":[51],"named":[53],"entity":[54],"annotated":[55],"bilingual":[56,68],"English-Vietnamese":[57,81],"corpus.":[58],"Our":[59,111],"system":[60,75],"uses":[61],"expansion":[62],"heuristics":[63],"candidate":[65,71],"generation":[66],"features":[69],"selection.":[72],"The":[73],"proposed":[74],"outperforms":[76],"the":[77],"state-of-the-art":[78],"Alignment,":[84],"increasing":[85],"F1-score":[86,103],"from":[87],"82.68%":[88],"86.57%.":[90],"Moreover,":[91],"Vietnamese":[92],"Recognition":[95],"performance":[96],"improves":[97],"by":[98],"23.41%":[99],"terms":[101],"of":[102],"compared":[104],"Conditional":[106],"Random":[107],"Field":[108],"model":[109],"(StanfordNER).":[110],"can":[113],"be":[114],"generalized":[115],"develop":[117],"other":[120],"languages.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
