{"id":"https://openalex.org/W3012283907","doi":"https://doi.org/10.5220/0009167205220529","title":"Transfer Learning for Digital Heritage Collections: Comparing Neural Machine Translation at the Subword-level and Character-level","display_name":"Transfer Learning for Digital Heritage Collections: Comparing Neural Machine Translation at the Subword-level and Character-level","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3012283907","doi":"https://doi.org/10.5220/0009167205220529","mag":"3012283907"},"language":"en","primary_location":{"id":"doi:10.5220/0009167205220529","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0009167205220529","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0009167205220529","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004688187","display_name":"Nikolay Banar","orcid":"https://orcid.org/0000-0001-9517-5791"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nikolay Banar","raw_affiliation_strings":["Computational Linguistics and Psycholinguistics Research Center, University of Antwerp, Belgium, Antwerp Centre for Digital Humanities and Literary Criticism, University of Antwerp, Belgium, --- Select a Country ---","Antwerp Centre for Digital Humanities and Literary Criticism, University of Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics and Psycholinguistics Research Center, University of Antwerp, Belgium, Antwerp Centre for Digital Humanities and Literary Criticism, University of Antwerp, Belgium, --- Select a Country ---","institution_ids":["https://openalex.org/I149213910"]},{"raw_affiliation_string":"Antwerp Centre for Digital Humanities and Literary Criticism, University of Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042627573","display_name":"Karine Lasaracina","orcid":"https://orcid.org/0009-0006-1732-6607"},"institutions":[{"id":"https://openalex.org/I4210138313","display_name":"Royal Museums of Fine Arts of Belgium","ror":"https://ror.org/03z601r05","country_code":"BE","type":"archive","lineage":["https://openalex.org/I4210138313"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Karine Lasaracina","raw_affiliation_strings":["Royal Museums of Fine Arts of Belgium, Brussels, Belgium, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Museums of Fine Arts of Belgium, Brussels, Belgium, --- Select a Country ---","institution_ids":["https://openalex.org/I4210138313"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083411784","display_name":"Walter Daelemans","orcid":"https://orcid.org/0000-0002-9832-7890"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Walter Daelemans","raw_affiliation_strings":["Computational Linguistics and Psycholinguistics Research Center, University of Antwerp, Belgium, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics and Psycholinguistics Research Center, University of Antwerp, Belgium, --- Select a Country ---","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068789709","display_name":"Mike Kestemont","orcid":"https://orcid.org/0000-0003-3590-693X"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Mike Kestemont","raw_affiliation_strings":["Computational Linguistics and Psycholinguistics Research Center, University of Antwerp, Belgium, Antwerp Centre for Digital Humanities and Literary Criticism, University of Antwerp, Belgium, --- Select a Country ---","Antwerp Centre for Digital Humanities and Literary Criticism, University of Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics and Psycholinguistics Research Center, University of Antwerp, Belgium, Antwerp Centre for Digital Humanities and Literary Criticism, University of Antwerp, Belgium, --- Select a Country ---","institution_ids":["https://openalex.org/I149213910"]},{"raw_affiliation_string":"Antwerp Centre for Digital Humanities and Literary Criticism, University of Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4062,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68435368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"522","last_page":"529"},"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":0.9994999766349792,"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":0.9878000020980835,"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/computer-science","display_name":"Computer science","score":0.8379762172698975},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7124236822128296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6919453740119934},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6730359792709351},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6575777530670166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6572175025939941},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6171631813049316},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6064754724502563},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5490900278091431},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5030927062034607},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4411907196044922},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15541526675224304},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09860628843307495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379762172698975},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7124236822128296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6919453740119934},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6730359792709351},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6575777530670166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6572175025939941},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6171631813049316},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6064754724502563},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5490900278091431},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5030927062034607},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4411907196044922},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15541526675224304},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09860628843307495},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0009167205220529","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0009167205220529","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:c:irua:167224","is_oa":false,"landing_page_url":"https://hdl.handle.net/10067/1672240151162165141","pdf_url":null,"source":{"id":"https://openalex.org/S4306401849","display_name":"Institutional Repository University of Antwerp (University of Antwerp)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149213910","host_organization_name":"University of Antwerp","host_organization_lineage":["https://openalex.org/I149213910"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.5220/0009167205220529","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0009167205220529","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W338621447","https://openalex.org/W1522301498","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2250342921","https://openalex.org/W2512848817","https://openalex.org/W2531207078","https://openalex.org/W2550821151","https://openalex.org/W2903188467","https://openalex.org/W2950621961","https://openalex.org/W2951559648","https://openalex.org/W2962732637","https://openalex.org/W2962784628","https://openalex.org/W2963251942","https://openalex.org/W2963324947","https://openalex.org/W2963506925","https://openalex.org/W2963887123"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W1997182898"],"abstract_inverted_index":{"Transfer":[0],"learning":[1,37,94],"via":[2],"pre-training":[3],"has":[4],"become":[5],"an":[6,99],"important":[7],"strategy":[8],"for":[9,46,92,144],"the":[10,39,62,150,156,166,181,186],"efficient":[11],"application":[12],"of":[13,41,51,169],"NLP":[14],"methods":[15],"in":[16,32,38,84,101,122,185],"domains":[17],"where":[18],"only":[19],"limited":[20],"training":[21],"data":[22],"is":[23,58,80],"available.This":[24],"paper":[25],"reports":[26],"on":[27,114,127,136,149],"a":[28,81,89,105,108,115,123,128],"focused":[29],"case":[30],"study":[31],"which":[33,102],"we":[34,103,153],"apply":[35],"transfer":[36,93],"context":[40],"neural":[42,54],"machine":[43,55],"translation":[44,56,175],"(French-Dutch)":[45],"cultural":[47,187],"heritage":[48,188],"metadata":[49],"(i.e.titles":[50],"artistic":[52],"works).Nowadays,":[53],"(NMT)":[57],"commonly":[59],"applied":[60],"at":[61],"subword":[63],"level":[64],"using":[65],"byte-pair":[66],"encoding":[67],"(BPE),":[68],"because":[69],"word-level":[70],"models":[71,113,148],"struggle":[72],"with":[73],"rare":[74],"and":[75,119,134,146],"out-of-vocabulary":[76],"words.Because":[77],"unseen":[78],"vocabulary":[79],"significant":[82],"issue":[83],"domain":[85],"adaptation,":[86],"BPE":[87],"seems":[88],"better":[90],"fit":[91],"across":[95],"text":[96],"varieties.We":[97],"discuss":[98],"experiment":[100],"compare":[104],"subword-level":[106,183],"to":[107,180],"character-level":[109,145,157,174],"NMT":[110],"approach.We":[111],"pre-trained":[112],"large,":[116],"generic":[117],"corpus":[118],"fine-tuned":[120],"them":[121],"two-stage":[124],"process:":[125],"first,":[126],"domain-specific":[129],"dataset":[130],"extracted":[131],"from":[132],"Wikipedia,":[133],"then":[135],"our":[137,139],"metadata.While":[138],"experiments":[140],"show":[141],"comparable":[142],"performance":[143,163],"BPEbased":[147],"general":[151],"dataset,":[152],"demonstrate":[154],"that":[155,173],"approach":[158,184],"nevertheless":[159],"yields":[160],"major":[161],"downstream":[162],"gains":[164],"during":[165],"subsequent":[167],"stages":[168],"fine-tuning.We":[170],"therefore":[171],"conclude":[172],"can":[176],"be":[177],"beneficial":[178],"compared":[179],"popular":[182],"domain.":[189]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}