{"id":"https://openalex.org/W3096841893","doi":null,"title":"Learning Contextualised Cross-lingual Word Embeddings for Extremely Low-Resource Languages Using Parallel Corpora.","display_name":"Learning Contextualised Cross-lingual Word Embeddings for Extremely Low-Resource Languages Using Parallel Corpora.","publication_year":2020,"publication_date":"2020-10-27","ids":{"openalex":"https://openalex.org/W3096841893","mag":"3096841893"},"language":"en","primary_location":{"id":"mag:3096841893","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.14649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.14649","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Takashi Wada","orcid":"https://orcid.org/0009-0006-1586-7530","observed_orcids":["https://orcid.org/0009-0006-1586-7530"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Wada","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-1586-7530","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034538103","display_name":"Tomoharu Iwata","orcid":"https://orcid.org/0000-0003-4425-1971","observed_orcids":["https://orcid.org/0000-0003-4425-1971"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoharu Iwata","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4425-1971","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072032804","display_name":"Y\u016bji Matsumoto","orcid":"https://orcid.org/0000-0003-4946-9574","observed_orcids":["https://orcid.org/0000-0003-4946-9574"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Y\u016bji Matsumoto","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4946-9574","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103085805","display_name":"Timothy Baldwin","orcid":"https://orcid.org/0000-0002-4445-1386","observed_orcids":["https://orcid.org/0000-0002-4445-1386","https://orcid.org/0000-0003-4525-6950"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy Baldwin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4445-1386","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032767467","display_name":"Jey Han Lau","orcid":"https://orcid.org/0000-0002-1647-4628","observed_orcids":["https://orcid.org/0000-0002-1647-4628"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jey Han Lau","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1647-4628","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7846999764442444,"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":0.7846999764442444,"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":0.1988999992609024,"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":0.0017999999690800905,"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/cross-lingual-word-embeddings","display_name":"cross-lingual word embeddings","score":0.9950000047683716},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.9290000200271606},{"id":"https://openalex.org/keywords/bidirectional-translation","display_name":"bidirectional translation","score":0.753000020980835},{"id":"https://openalex.org/keywords/weight-sharing","display_name":"parameter sharing","score":0.7009999752044678},{"id":"https://openalex.org/keywords/subword-embeddings","display_name":"subword embeddings","score":0.871999979019165},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.8500000238418579},{"id":"https://openalex.org/keywords/bilingual-lexicon-induction","display_name":"bilingual lexicon induction","score":0.8980000019073486},{"id":"https://openalex.org/keywords/word-alignment","display_name":"word alignment","score":0.9269999861717224},{"id":"https://openalex.org/keywords/shipibo-konibo","display_name":"Shipibo-Konibo","score":0.9980000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374523520469666},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7004349231719971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6798055171966553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6404147148132324},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6330133676528931},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5685627460479736},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5095475316047668},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5017261505126953},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4797286093235016},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4146912097930908},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.403156042098999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3307992219924927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17870941758155823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08461582660675049},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3096841893","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.14649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3096841893","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.14649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W77482081","https://openalex.org/W1480519300","https://openalex.org/W1484641689","https://openalex.org/W1614298861","https://openalex.org/W2006969979","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2131988669","https://openalex.org/W2141532438","https://openalex.org/W2148708890","https://openalex.org/W2156985047","https://openalex.org/W2210801195","https://openalex.org/W2229725139","https://openalex.org/W2251765408","https://openalex.org/W2294774419","https://openalex.org/W2295781714","https://openalex.org/W2493916176","https://openalex.org/W2514713644","https://openalex.org/W2549416390","https://openalex.org/W2574132677","https://openalex.org/W2607106700","https://openalex.org/W2626778328","https://openalex.org/W2740132093","https://openalex.org/W2741986357","https://openalex.org/W2764124976","https://openalex.org/W2775632580","https://openalex.org/W2787560479","https://openalex.org/W2788463229","https://openalex.org/W2795609003","https://openalex.org/W2798389157","https://openalex.org/W2805049284","https://openalex.org/W2805736358","https://openalex.org/W2884066185","https://openalex.org/W2885185669","https://openalex.org/W2891844856","https://openalex.org/W2891896107","https://openalex.org/W2896457183","https://openalex.org/W2913077545","https://openalex.org/W2941819978","https://openalex.org/W2944852028","https://openalex.org/W2949402715","https://openalex.org/W2953242939","https://openalex.org/W2963002901","https://openalex.org/W2963118869","https://openalex.org/W2964121744","https://openalex.org/W2995118574","https://openalex.org/W3013840636","https://openalex.org/W3022467813","https://openalex.org/W3030047911","https://openalex.org/W3030402048","https://openalex.org/W3034617741","https://openalex.org/W3103915675","https://openalex.org/W3104881680","https://openalex.org/W3155609600"],"related_works":["https://openalex.org/W3213710625","https://openalex.org/W7169724184","https://openalex.org/W7168280137","https://openalex.org/W2981960436","https://openalex.org/W2741986357","https://openalex.org/W3119707607","https://openalex.org/W3136927871","https://openalex.org/W4401044196","https://openalex.org/W2997327944","https://openalex.org/W3030402048"],"abstract_inverted_index":{"We":[0,63,84],"propose":[1,65],"a":[2,14,19,59,66,118],"new":[3],"approach":[4],"for":[5,121,139],"learning":[6,140],"contextualised":[7],"cross-lingual":[8,141],"word":[9,27,56,71,107],"embeddings":[10,28,57,74],"based":[11],"only":[12],"on":[13,88,102],"small":[15],"parallel":[16],"corpus":[17],"(e.g.":[18],"few":[20],"hundred":[21],"sentence":[22],"pairs).":[23],"Our":[24,100],"method":[25,68],"obtains":[26],"via":[29],"an":[30,133],"LSTM-based":[31],"encoder-decoder":[32,134],"model":[33,46,52,113,136],"that":[34,111],"performs":[35],"bidirectional":[36],"translation":[37,135],"and":[38,72,98,106],"reconstruction":[39],"of":[40,78],"the":[41,55],"input":[42],"sentence.":[43],"Through":[44],"sharing":[45],"parameters":[47],"among":[48],"different":[49,82],"languages,":[50,93],"our":[51,86,112],"jointly":[53],"trains":[54],"in":[58,144],"common":[60,131],"multilingual":[61],"space.":[62],"also":[64],"simple":[67],"to":[69,75,130],"combine":[70],"subword":[73],"make":[76],"use":[77],"orthographic":[79],"similarities":[80],"across":[81],"languages.":[83],"base":[85],"experiments":[87,101],"real-world":[89],"data":[90],"from":[91],"endangered":[92],"namely":[94],"Yongning":[95],"Na,":[96],"Shipibo-Konibo":[97],"Griko.":[99],"bilingual":[103],"lexicon":[104],"induction":[105],"alignment":[108],"tasks":[109],"show":[110],"outperforms":[114],"existing":[115],"methods":[116],"by":[117],"large":[119],"margin":[120],"most":[122],"language":[123],"pairs.":[124],"These":[125],"results":[126],"demonstrate":[127],"that,":[128],"contrary":[129],"belief,":[132],"is":[137],"beneficial":[138],"representations,":[142],"even":[143],"extremely":[145],"low-resource":[146],"scenarios.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-11-09T00:00:00"}