{"id":"https://openalex.org/W3193922060","doi":"https://doi.org/10.1145/3464427","title":"Improving Data Augmentation for Low-Resource NMT Guided by POS-Tagging and Paraphrase Embedding","display_name":"Improving Data Augmentation for Low-Resource NMT Guided by POS-Tagging and Paraphrase Embedding","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3193922060","doi":"https://doi.org/10.1145/3464427","mag":"3193922060"},"language":"en","primary_location":{"id":"doi:10.1145/3464427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3464427","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/A5037218373","display_name":"Mieradilijiang Maimaiti","orcid":"https://orcid.org/0000-0002-4231-6519"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mieradilijiang Maimaiti","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086000078","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-3087-242X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091587552","display_name":"Huanbo Luan","orcid":"https://orcid.org/0000-0003-3938-119X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanbo Luan","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023152858","display_name":"Zegao Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zegao Pan","raw_affiliation_strings":["School of Software, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046448314","display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maosong Sun","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2284,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83130144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"6","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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/paraphrase","display_name":"Paraphrase","score":0.8915438652038574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8056402802467346},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7792210578918457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.670635461807251},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5940502285957336},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5790970921516418},{"id":"https://openalex.org/keywords/adjective","display_name":"Adjective","score":0.5633720755577087},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5446395874023438},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5130871534347534},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.465290904045105},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44295838475227356},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4383637011051178},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.43812844157218933},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4109658896923065},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18106001615524292},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.15580075979232788}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.8915438652038574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8056402802467346},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7792210578918457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.670635461807251},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5940502285957336},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5790970921516418},{"id":"https://openalex.org/C2777683214","wikidata":"https://www.wikidata.org/wiki/Q34698","display_name":"Adjective","level":3,"score":0.5633720755577087},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5446395874023438},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5130871534347534},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.465290904045105},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44295838475227356},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4383637011051178},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.43812844157218933},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4109658896923065},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18106001615524292},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.15580075979232788},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3464427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3464427","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":[],"awards":[{"id":"https://openalex.org/G112481924","display_name":null,"funder_award_id":"2017YFB0202204","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8656468031","display_name":null,"funder_award_id":"61925601, and 61772302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2010576059","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2118434577","https://openalex.org/W2149327368","https://openalex.org/W2152263452","https://openalex.org/W2153653739","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2250473257","https://openalex.org/W2251743902","https://openalex.org/W2579496717","https://openalex.org/W2610850660","https://openalex.org/W2762058688","https://openalex.org/W2803739890","https://openalex.org/W2888519496","https://openalex.org/W2903268415","https://openalex.org/W2945381748","https://openalex.org/W2946068894","https://openalex.org/W2949973181","https://openalex.org/W2950577311","https://openalex.org/W2962784628","https://openalex.org/W2963088995","https://openalex.org/W2963099225","https://openalex.org/W2963216553","https://openalex.org/W2963247703","https://openalex.org/W2963357083","https://openalex.org/W2964007535","https://openalex.org/W2970286654","https://openalex.org/W2971089354","https://openalex.org/W2984500026","https://openalex.org/W2990804422","https://openalex.org/W2998215494","https://openalex.org/W3034898894","https://openalex.org/W3098341425","https://openalex.org/W4251372957"],"related_works":["https://openalex.org/W191017350","https://openalex.org/W4206666510","https://openalex.org/W2018298289","https://openalex.org/W2782520308","https://openalex.org/W3175194702","https://openalex.org/W2251069562","https://openalex.org/W2167109146","https://openalex.org/W2135511601","https://openalex.org/W2170543300","https://openalex.org/W4391992322"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,23,177],"is":[2],"an":[3],"approach":[4],"for":[5,32],"several":[6],"text":[7],"generation":[8],"tasks.":[9],"Generally,":[10],"in":[11,17,38,47,126,140,190],"the":[12,48,55,67,78,84,99,107,112,120,127,131,141,148,162,186],"machine":[13],"translation":[14],"paradigm,":[15],"mainly":[16,36],"low-resource":[18,187],"language":[19,188,192],"scenarios,":[20],"many":[21],"data":[22,35,68],"methods":[24,52,184],"have":[25],"been":[26],"proposed.":[27],"The":[28],"most":[29],"used":[30],"approaches":[31],"generating":[33],"pseudo":[34],"lay":[37],"word":[39,116,121,125],"omission,":[40],"random":[41],"sampling,":[42],"or":[43],"replacing":[44,83],"some":[45,170],"words":[46,136,139,155],"text.":[49],"However,":[50],"previous":[51,182],"barely":[53],"guarantee":[54],"quality":[56],"of":[57,111,123],"augmented":[58],"data.":[59],"In":[60,144],"this":[61],"work,":[62],"we":[63,76,146],"try":[64],"to":[65,151,156,165,169,199],"build":[66],"by":[69,82,197],"using":[70],"paraphrase":[71,100,113],"embedding":[72,122],"and":[73,94,102,118,137,160],"POS-Tagging.":[74],"Namely,":[75],"generate":[77],"fake":[79],"monolingual":[80],"corpus":[81,109],"main":[85],"four":[86,195],"POS-Tagging":[87,163],"labels,":[88],"such":[89],"as":[90],"noun,":[91],"adjective,":[92],"adverb,":[93],"verb,":[95],"based":[96],"on":[97,185],"both":[98],"table":[101,114],"their":[103],"similarity.":[104],"We":[105],"select":[106],"bigger":[108],"size":[110],"with":[115],"level":[117],"obtain":[119],"each":[124],"table,":[128],"then":[129],"calculate":[130],"cosine":[132],"similarity":[133],"between":[134],"these":[135],"tagged":[138],"original":[142],"sequence.":[143],"addition,":[145],"exploit":[147],"ranking":[149],"algorithm":[150],"choose":[152],"highly":[153],"similar":[154],"reduce":[157],"semantic":[158],"errors":[159],"leverage":[161],"replacement":[164],"mitigate":[166],"syntactic":[167],"error":[168],"extent.":[171],"Experimental":[172],"results":[173],"show":[174],"that":[175],"our":[176],"method":[178],"consistently":[179],"outperforms":[180],"all":[181],"SOTA":[183],"pairs":[189,193],"seven":[191],"from":[194],"corpora":[196],"1.16":[198],"2.39":[200],"BLEU":[201],"points.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}