{"id":"https://openalex.org/W3139121486","doi":"https://doi.org/10.1145/3448216","title":"Finding Better Subwords for Tibetan Neural Machine Translation","display_name":"Finding Better Subwords for Tibetan Neural Machine Translation","publication_year":2021,"publication_date":"2021-03-15","ids":{"openalex":"https://openalex.org/W3139121486","doi":"https://doi.org/10.1145/3448216","mag":"3139121486"},"language":"en","primary_location":{"id":"doi:10.1145/3448216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448216","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3448216","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101701181","display_name":"Yachao Li","orcid":"https://orcid.org/0000-0002-9423-9922"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yachao Li","raw_affiliation_strings":["China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042484772","display_name":"Jing Jiang","orcid":"https://orcid.org/0000-0002-5648-2323"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Jiang","raw_affiliation_strings":["China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002649810","display_name":"Yangji JIA","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Yangji","raw_affiliation_strings":["China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101783869","display_name":"Ning Ma","orcid":"https://orcid.org/0000-0001-9684-001X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Ma","raw_affiliation_strings":["China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China\u2019s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8396,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78008606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":"2","first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9959999918937683,"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":0.980400025844574,"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/syllable","display_name":"Syllable","score":0.8075798153877258},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7513648271560669},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7012029886245728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6704900860786438},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6614775061607361},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6165807843208313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5716404914855957},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5552049279212952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.550495982170105},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5439839363098145},{"id":"https://openalex.org/keywords/carry","display_name":"Carry (investment)","score":0.5332037806510925},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4926944077014923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4613940715789795},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33377230167388916},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2364237904548645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.159423828125}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.8075798153877258},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7513648271560669},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7012029886245728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704900860786438},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6614775061607361},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6165807843208313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716404914855957},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5552049279212952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.550495982170105},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5439839363098145},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.5332037806510925},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4926944077014923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4613940715789795},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33377230167388916},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2364237904548645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.159423828125},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3448216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448216","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3448216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448216","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2700487867","display_name":"\u878d\u5408\u591a\u7279\u5f81\u7684\u85cf\u6587\u4e8b\u4ef6\u5c5e\u6027\u4fe1\u606f\u62bd\u53d6\u7406\u8bba\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61762076","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1963938256","https://openalex.org/W2101105183","https://openalex.org/W2107878631","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2371519299","https://openalex.org/W2552839021","https://openalex.org/W2786173426","https://openalex.org/W2883527841","https://openalex.org/W2888520903","https://openalex.org/W2952524847","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963212250","https://openalex.org/W2963599677","https://openalex.org/W2963913268","https://openalex.org/W2963979492","https://openalex.org/W2963991316","https://openalex.org/W2964045208","https://openalex.org/W3016012197"],"related_works":["https://openalex.org/W2793180915","https://openalex.org/W2386495035","https://openalex.org/W1582047458","https://openalex.org/W1514266315","https://openalex.org/W2071291085","https://openalex.org/W1490628945","https://openalex.org/W2883671469","https://openalex.org/W4313650408","https://openalex.org/W4310449030","https://openalex.org/W3113535064"],"abstract_inverted_index":{"Subword":[0],"segmentation":[1,85,108,122],"plays":[2],"an":[3],"important":[4],"role":[5],"in":[6,104],"Tibetan":[7,15,50,65,73],"neural":[8],"machine":[9],"translation":[10,102],"(NMT).":[11],"The":[12,58,92],"structure":[13],"of":[14,18,24,27,34,37,98,143],"words":[16,22],"consists":[17,33],"two":[19,47,83],"levels.":[20],"First,":[21],"consist":[23],"a":[25,31,35],"sequence":[26,36],"syllables,":[28,66],"and":[29,55,67,126],"then":[30],"syllable":[32],"characters.":[38,74],"According":[39],"to":[40,139],"this":[41],"special":[42],"word":[43],"structure,":[44],"we":[45,77],"propose":[46],"methods":[48,86],"for":[49],"subword":[51,84,107,121],"segmentation,":[52],"namely":[53],"syllable-based":[54],"character-based":[56,120],"methods.":[57],"former":[59],"generates":[60],"subwords":[61],"based":[62,71,109],"on":[63,72,87,110],"the":[64,68,106,140],"latter":[69],"is":[70,123],"In":[75],"addition,":[76],"carry":[78],"out":[79],"experiments":[80],"with":[81],"these":[82],"low-resource":[88],"Tibetan-to-Chinese":[89],"NMT,":[90],"respectively.":[91],"experimental":[93,133],"results":[94,134],"show":[95],"that":[96],"both":[97],"them":[99],"can":[100,113,130],"improve":[101],"performance,":[103],"which":[105],"character":[111],"sequences":[112],"achieve":[114,131],"better":[115,132],"results.":[116],"Overall,":[117],"our":[118],"proposed":[119],"more":[124],"simple":[125],"effective.":[127],"Moreover,":[128],"it":[129],"without":[135],"paying":[136],"much":[137],"attention":[138],"linguistic":[141],"features":[142],"Tibetan.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
