{"id":"https://openalex.org/W2888831408","doi":"https://doi.org/10.18653/v1/d18-1366","title":"Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations","display_name":"Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888831408","doi":"https://doi.org/10.18653/v1/d18-1366","mag":"2888831408"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1366","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1366","pdf_url":"https://www.aclweb.org/anthology/D18-1366.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1366.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073858017","display_name":"Aditi Chaudhary","orcid":"https://orcid.org/0009-0002-4658-4040"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditi Chaudhary","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252779","display_name":"Chunting Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunting Zhou","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008257790","display_name":"Lori Levin","orcid":"https://orcid.org/0000-0003-0831-3063"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lori Levin","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109861718","display_name":"Jaime Carbonell","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaime Carbonell","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3285","last_page":"3295"},"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/T13629","display_name":"Text Readability and Simplification","score":0.983299970626831,"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/bengali","display_name":"Bengali","score":0.9451825618743896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8134205341339111},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7787866592407227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7207801342010498},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.6805505156517029},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.6113380193710327},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5947751402854919},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5925121307373047},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.556732177734375},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.47614431381225586},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4747522175312042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3427601456642151},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3134337067604065},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11703690886497498}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9451825618743896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134205341339111},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7787866592407227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7207801342010498},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6805505156517029},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.6113380193710327},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5947751402854919},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5925121307373047},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.556732177734375},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.47614431381225586},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4747522175312042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3427601456642151},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3134337067604065},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11703690886497498},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d18-1366","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1366","pdf_url":"https://www.aclweb.org/anthology/D18-1366.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1808.09500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.09500","pdf_url":"https://arxiv.org/pdf/1808.09500","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},{"id":"mag:2888831408","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.09500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.1808.09500","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.09500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1366","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1366","pdf_url":"https://www.aclweb.org/anthology/D18-1366.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"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/W2888831408.pdf","grobid_xml":"https://content.openalex.org/works/W2888831408.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2004316800","https://openalex.org/W2270364989","https://openalex.org/W2337363174","https://openalex.org/W2475191182","https://openalex.org/W2573169100","https://openalex.org/W2575512508","https://openalex.org/W2625541525","https://openalex.org/W2757931423","https://openalex.org/W2758640791","https://openalex.org/W2787560479","https://openalex.org/W2792296443","https://openalex.org/W2949548130","https://openalex.org/W2950577311","https://openalex.org/W2952566282","https://openalex.org/W2964005834","https://openalex.org/W3104723404"],"related_works":["https://openalex.org/W2964144280","https://openalex.org/W3029311208","https://openalex.org/W3185358959","https://openalex.org/W2013997717","https://openalex.org/W3038489922","https://openalex.org/W2210138121","https://openalex.org/W3161059290","https://openalex.org/W2475191182","https://openalex.org/W2905037098","https://openalex.org/W3199212312","https://openalex.org/W2998844548","https://openalex.org/W2963739452","https://openalex.org/W2762484717","https://openalex.org/W3184501572","https://openalex.org/W3093536026","https://openalex.org/W2998280981","https://openalex.org/W3206914982","https://openalex.org/W3122978153","https://openalex.org/W2969143370","https://openalex.org/W2807629530"],"abstract_inverted_index":{"Much":[0],"work":[1],"in":[2,57,126],"Natural":[3],"Language":[4],"Processing":[5],"(NLP)":[6],"has":[7],"been":[8],"for":[9,23,77,115,120],"resource-rich":[10],"languages,":[11,79,94],"making":[12],"generalization":[13,25],"to":[14,26],"new,":[15],"less-resourced":[16],"languages":[17,28],"challenging.":[18],"We":[19,66,122],"present":[20],"two":[21],"approaches":[22,72],"improving":[24],"lowresourced":[27],"by":[29],"adapting":[30],"continuous":[31],"word":[32],"representations":[33],"using":[34],"linguistically":[35],"motivated":[36],"subword":[37],"units:":[38],"phonemes,":[39],"morphemes":[40],"and":[41,52,84,89,95,117,136],"graphemes.":[42],"Our":[43],"method":[44],"requires":[45],"neither":[46],"parallel":[47],"corpora":[48],"nor":[49],"bilingual":[50],"dictionaries":[51],"provides":[53],"a":[54,109],"significant":[55],"gain":[56],"performance":[58],"over":[59],"previous":[60],"methods":[61],"relying":[62],"on":[63,73,99],"these":[64],"resources.":[65],"demonstrate":[67],"the":[68,127],"effectiveness":[69],"of":[70,86,111],"our":[71],"Named":[74],"Entity":[75],"Recognition":[76],"four":[78],"namely":[80],"Uyghur,":[81],"Turkish,":[82],"Bengali":[83,90],"Hindi,":[85],"which":[87],"Uyghur":[88,116],"are":[91],"low":[92],"resource":[93],"also":[96,123],"perform":[97],"experiments":[98],"Machine":[100],"Translation.":[101],"Exploiting":[102],"subwords":[103],"with":[104],"transfer":[105],"learning":[106],"gives":[107],"us":[108],"boost":[110],"+15.2":[112],"NER":[113],"F1":[114,119,135],"+9.7":[118],"Bengali.":[121],"show":[124],"improvements":[125],"monolingual":[128],"setting":[129],"where":[130],"we":[131],"achieve":[132],"(avg.)":[133,137],"+3":[134],"+1.35":[138],"BLEU.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-08-03T00:00:00"}