{"id":"https://openalex.org/W2798603802","doi":"https://doi.org/10.18653/v1/p18-2064","title":"Judicious Selection of Training Data in Assisting Language for Multilingual Neural NER","display_name":"Judicious Selection of Training Data in Assisting Language for Multilingual Neural NER","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798603802","doi":"https://doi.org/10.18653/v1/p18-2064","mag":"2798603802"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-2064","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2064","pdf_url":"https://www.aclweb.org/anthology/P18-2064.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-2064.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000493089","display_name":"Rudra Murthy","orcid":"https://orcid.org/0000-0002-6236-1931"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rudra Murthy","raw_affiliation_strings":["Center for Indian Language Technology (CFILT) Department of Computer Science and Engineering IIT Bombay, India"],"affiliations":[{"raw_affiliation_string":"Center for Indian Language Technology (CFILT) Department of Computer Science and Engineering IIT Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052909911","display_name":"Anoop Kunchukuttan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anoop Kunchukuttan","raw_affiliation_strings":["Microsoft AI & Research, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100828","display_name":"Pushpak Bhattacharyya","orcid":"https://orcid.org/0000-0001-5319-5508"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pushpak Bhattacharyya","raw_affiliation_strings":["Center for Indian Language Technology (CFILT) Department of Computer Science and Engineering IIT Bombay, India"],"affiliations":[{"raw_affiliation_string":"Center for Indian Language Technology (CFILT) Department of Computer Science and Engineering IIT Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000493089"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.9773,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81371007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"406"},"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9710999727249146,"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/computer-science","display_name":"Computer science","score":0.8466653823852539},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.765099048614502},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7085199356079102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6213418841362},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5822396278381348},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5809834003448486},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5808900594711304},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5500584244728088},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.527205765247345},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5039383769035339},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.46034032106399536},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3700979948043823},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.1174716055393219},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11655360460281372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466653823852539},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.765099048614502},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7085199356079102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6213418841362},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5822396278381348},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5809834003448486},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5808900594711304},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5500584244728088},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.527205765247345},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5039383769035339},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.46034032106399536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3700979948043823},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.1174716055393219},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11655360460281372},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-2064","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2064","pdf_url":"https://www.aclweb.org/anthology/P18-2064.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-2064","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2064","pdf_url":"https://www.aclweb.org/anthology/P18-2064.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798603802.pdf","grobid_xml":"https://content.openalex.org/works/W2798603802.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W202361227","https://openalex.org/W572280432","https://openalex.org/W1905522558","https://openalex.org/W2117278770","https://openalex.org/W2144578941","https://openalex.org/W2158899491","https://openalex.org/W2183945364","https://openalex.org/W2251467004","https://openalex.org/W2296283641","https://openalex.org/W2308486447","https://openalex.org/W2493916176","https://openalex.org/W2527833599","https://openalex.org/W2792234060","https://openalex.org/W2915429162","https://openalex.org/W2952087486","https://openalex.org/W2952230511","https://openalex.org/W2962902328","https://openalex.org/W2963208801","https://openalex.org/W2964125718","https://openalex.org/W2964311143"],"related_works":["https://openalex.org/W3199871245","https://openalex.org/W2915436880","https://openalex.org/W1964783010","https://openalex.org/W3198729192","https://openalex.org/W3121292129","https://openalex.org/W3208095355","https://openalex.org/W4295038225","https://openalex.org/W4285819037","https://openalex.org/W2177370417","https://openalex.org/W2800535933"],"abstract_inverted_index":{"Multilingual":[0],"learning":[1],"for":[2,14],"Neural":[3],"Named":[4],"Entity":[5],"Recognition":[6],"(NNER)":[7],"involves":[8],"jointly":[9],"training":[10,84,109],"a":[11,71],"neural":[12],"network":[13],"multiple":[15],"languages.":[16,37],"Typically,":[17],"the":[18,22,28,34,41,44,48,53,60,81,87],"goal":[19],"is":[20],"improving":[21],"NER":[23,99],"performance":[24,100],"of":[25,27,47,62],"one":[26],"languages":[29,57],"(the":[30],"primary":[31,54],"language)":[32],"using":[33],"other":[35],"assisting":[36,56,88],"We":[38,90],"show":[39,92],"that":[40,93],"divergence":[42,77],"in":[43,86,101],"tag":[45],"distributions":[46],"common":[49],"named":[50],"entities":[51],"between":[52],"and":[55],"can":[58],"reduce":[59],"effectiveness":[61],"multilingual":[63],"learning.":[64],"To":[65],"alleviate":[66],"this":[67],"problem,":[68],"we":[69],"propose":[70],"metric":[72],"based":[73],"on":[74],"symmetric":[75],"KL":[76],"to":[78],"filter":[79],"out":[80],"highly":[82],"divergent":[83],"instances":[85],"language.":[89],"empirically":[91],"our":[94],"data":[95],"selection":[96],"strategy":[97],"improves":[98],"many":[102],"languages,":[103],"including":[104],"those":[105],"with":[106],"very":[107],"limited":[108],"data.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}