{"id":"https://openalex.org/W2531841301","doi":"https://doi.org/10.1145/2990191","title":"An Approach to Construct a Named Entity Annotated English-Vietnamese Bilingual Corpus","display_name":"An Approach to Construct a Named Entity Annotated English-Vietnamese Bilingual Corpus","publication_year":2016,"publication_date":"2016-10-14","ids":{"openalex":"https://openalex.org/W2531841301","doi":"https://doi.org/10.1145/2990191","mag":"2531841301"},"language":"en","primary_location":{"id":"doi:10.1145/2990191","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2990191","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/A5048517713","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0002-0884-1635"},"institutions":[{"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 H. B. Nguyen","raw_affiliation_strings":["University of Science, HCM City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science, HCM City, Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040236875","display_name":"\u0110i\u1ec1n \u0110inh","orcid":"https://orcid.org/0000-0003-2069-1016"},"institutions":[{"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":["University of Science, HCM City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science, HCM City, Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103075904","display_name":"Phuoc Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phuoc Tran","raw_affiliation_strings":["Ton Duc Thang University, HCM City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ton Duc Thang University, HCM City, Vietnam","institution_ids":["https://openalex.org/I141445968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8662,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84407783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"16","issue":"2","first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/vietnamese","display_name":"Vietnamese","score":0.8935891389846802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8507949113845825},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.8011334538459778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7478048205375671},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.742682933807373},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.717369556427002},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5807356834411621},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5482750535011292},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.4846216142177582},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4341639578342438},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1989685297012329}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8935891389846802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507949113845825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.8011334538459778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7478048205375671},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.742682933807373},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.717369556427002},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5807356834411621},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5482750535011292},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4846216142177582},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4341639578342438},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1989685297012329},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2990191","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2990191","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W187531367","https://openalex.org/W222053410","https://openalex.org/W800621058","https://openalex.org/W1603598191","https://openalex.org/W1667964228","https://openalex.org/W1973923101","https://openalex.org/W1977671488","https://openalex.org/W1991635536","https://openalex.org/W2006969979","https://openalex.org/W2038698865","https://openalex.org/W2051490926","https://openalex.org/W2070679081","https://openalex.org/W2101105183","https://openalex.org/W2119593077","https://openalex.org/W2122789960","https://openalex.org/W2123442489","https://openalex.org/W2124136969","https://openalex.org/W2133203418","https://openalex.org/W2137419020","https://openalex.org/W2138753018","https://openalex.org/W2150028966","https://openalex.org/W2151525026","https://openalex.org/W2156985047","https://openalex.org/W2158703834","https://openalex.org/W2165142900","https://openalex.org/W2241862190","https://openalex.org/W2251348249","https://openalex.org/W2251435463","https://openalex.org/W2432471317","https://openalex.org/W2741609678","https://openalex.org/W2930957955","https://openalex.org/W3140075257"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W2901718966","https://openalex.org/W3042674643","https://openalex.org/W3022757400","https://openalex.org/W1844055093","https://openalex.org/W61780229","https://openalex.org/W2077055222","https://openalex.org/W2973218968"],"abstract_inverted_index":{"Manually":[0],"constructing":[1],"an":[2,44,49,63],"annotated":[3,50],"Named":[4],"Entity":[5],"(NE)":[6],"in":[7,52,74],"a":[8,12,57,71,103],"bilingual":[9,54,58,72,106],"corpus":[10,55,60,69,73,110],"is":[11,20],"time-consuming,":[13],"labor--intensive,":[14],"and":[15,125,187],"expensive":[16],"process,":[17],"but":[18,118],"this":[19,40,68],"necessary":[21,130],"for":[22,131,183,192,202],"natural":[23],"language":[24,84],"processing":[25],"(NLP)":[26],"tasks":[27],"such":[28],"as":[29],"cross-lingual":[30,33],"information":[31,34,201],"retrieval,":[32],"extraction,":[35],"machine":[36,204],"translation,":[37],"etc.":[38],"In":[39,148],"article,":[41],"we":[42],"present":[43],"automatic":[45],"approach":[46,87,142],"to":[47,89,159,162,181,190,213],"construct":[48],"NE":[51,65,115,133,151,167],"English-Vietnamese":[53,150],"from":[56,81,157,179,188,211],"parallel":[59],"by":[61,101],"proposing":[62],"aligned":[64],"method.":[66],"Basing":[67],"on":[70],"which":[75,128],"the":[76,86,99,114,141,144,149,154,163,166,170,176,184,193,198,203,207],"initial":[77],"NEs":[78,92,96,100,124],"are":[79,129],"extracted":[80],"its":[82],"own":[83],"separately,":[85],"tries":[88],"correct":[90],"unrecognized":[91],"or":[93],"incorrectly":[94],"recognized":[95],"before":[97],"aligning":[98],"using":[102],"variety":[104],"of":[105,165],"constraints.":[107],"The":[108,136],"generated":[109],"not":[111],"only":[112],"improves":[113],"recognition":[116,168],"results":[117,138],"also":[119,173],"creates":[120],"alignments":[121],"between":[122],"English":[123,185],"Vietnamese":[126,194],"NEs,":[127],"training":[132],"translation":[134,205],"models.":[135],"experimental":[137],"show":[139],"that":[140],"outperforms":[143],"baseline":[145],"methods":[146],"effectively.":[147],"alignment":[152],"task,":[153],"F-measure":[155,177],"increases":[156,174,210],"68.58%":[158],"79.77%.":[160],"Thanks":[161],"improvement":[164],"quality,":[169],"proposed":[171],"method":[172],"significantly:":[175],"goes":[178],"84.85%":[180],"88.66%":[182],"side":[186],"75.71%":[189],"85.55%":[191],"side.":[195],"By":[196],"providing":[197],"additional":[199],"semantic":[200],"systems,":[206],"BLEU":[208],"score":[209],"33.04%":[212],"45.11%.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
