{"id":"https://openalex.org/W2987266335","doi":"https://doi.org/10.48550/arxiv.1911.06156","title":"Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding","display_name":"Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding","publication_year":2019,"publication_date":"2019-11-10","ids":{"openalex":"https://openalex.org/W2987266335","doi":"https://doi.org/10.48550/arxiv.1911.06156","mag":"2987266335"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1911.06156","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.06156","pdf_url":"https://arxiv.org/pdf/1911.06156","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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.06156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001619062","display_name":"Dhanasekar Sundararaman","orcid":"https://orcid.org/0000-0002-8192-8155","observed_orcids":["https://orcid.org/0000-0002-8192-8155"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sundararaman, Dhanasekar","raw_affiliation_strings":["Department of Electrical & Computer Engineering , Duke University Durham , NC 27708"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering , Duke University Durham , NC 27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Subramanian, Vivek","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subramanian, Vivek","raw_affiliation_strings":["Department of Electrical & Computer Engineering , Duke University Durham , NC 27708"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering , Duke University Durham , NC 27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031220156","display_name":"Guoyin Wang","orcid":"https://orcid.org/0000-0002-8521-5232","observed_orcids":["https://orcid.org/0000-0002-8521-5232","https://orcid.org/0000-0003-1954-4174"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Guoyin","raw_affiliation_strings":["Department of Electrical & Computer Engineering , Duke University Durham , NC 27708"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering , Duke University Durham , NC 27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032913967","display_name":"Shijing Si","orcid":"https://orcid.org/0000-0003-4346-2574","observed_orcids":["https://orcid.org/0000-0003-4346-2574"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si, Shijing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013573244","display_name":"Dinghan Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shen, Dinghan","raw_affiliation_strings":["Department of Electrical & Computer Engineering , Duke University Durham , NC 27708"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering , Duke University Durham , NC 27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391517","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-9599-8023","observed_orcids":["https://orcid.org/0000-0002-9599-8023"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Dong","raw_affiliation_strings":["Department of Electrical & Computer Engineering , Duke University Durham , NC 27708"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering , Duke University Durham , NC 27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016448581","display_name":"Lawrence Carin","orcid":"https://orcid.org/0000-0001-6277-7948","observed_orcids":["https://orcid.org/0000-0001-6277-7948"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carin, Lawrence","raw_affiliation_strings":["Department of Electrical & Computer Engineering , Duke University Durham , NC 27708"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering , Duke University Durham , NC 27708","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":42,"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":0.9032999873161316,"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":0.9032999873161316,"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":0.09160000085830688,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0006000000284984708,"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/bert-fine-tuning","display_name":"BERT fine-tuning","score":0.8220000267028809},{"id":"https://openalex.org/keywords/part-of-speech-features","display_name":"part-of-speech features","score":0.7350000143051147},{"id":"https://openalex.org/keywords/syntactic-information","display_name":"syntactic information","score":0.5849999785423279},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.8230000138282776},{"id":"https://openalex.org/keywords/english-german-translation","display_name":"English-German translation","score":0.8240000009536743},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.871999979019165},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"natural language understanding","score":0.8450000286102295},{"id":"https://openalex.org/keywords/glue-benchmark","display_name":"GLUE benchmark","score":0.8700000047683716},{"id":"https://openalex.org/keywords/attention-models","display_name":"attention-based models","score":0.699999988079071}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.678180456161499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769678592681885},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6545506119728088},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6399353742599487},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4534703195095062},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4252777099609375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38987427949905396},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33033132553100586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11638793349266052},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09210661053657532},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.04930415749549866},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1911.06156","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.06156","pdf_url":"https://arxiv.org/pdf/1911.06156","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1911.06156","doi":"https://doi.org/10.48550/arxiv.1911.06156","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.06156","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.06156","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.06156","pdf_url":"https://arxiv.org/pdf/1911.06156","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2987266335.pdf","grobid_xml":"https://content.openalex.org/works/W2987266335.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2410082850","https://openalex.org/W2519887557","https://openalex.org/W2549835527","https://openalex.org/W2626778328","https://openalex.org/W2773734397","https://openalex.org/W2789541106","https://openalex.org/W2798727047","https://openalex.org/W2799054028","https://openalex.org/W2948947170","https://openalex.org/W2962717763","https://openalex.org/W2962784628","https://openalex.org/W2962822108","https://openalex.org/W2963341956","https://openalex.org/W2963653811","https://openalex.org/W2963913268","https://openalex.org/W2964302946","https://openalex.org/W2971191050"],"related_works":["https://openalex.org/W4389323555","https://openalex.org/W3085499573","https://openalex.org/W3134979179","https://openalex.org/W3011573365","https://openalex.org/W3115557347","https://openalex.org/W4416058117","https://openalex.org/W7038392064","https://openalex.org/W4385574254","https://openalex.org/W4360605061","https://openalex.org/W3103729510"],"abstract_inverted_index":{"Attention-based":[0],"models":[1,48,66,91],"have":[2,43],"shown":[3,44],"significant":[4],"improvement":[5,107,126],"over":[6],"traditional":[7],"algorithms":[8],"in":[9,38,84],"several":[10],"NLP":[11],"tasks.":[12],"The":[13],"Transformer,":[14],"for":[15,89],"instance,":[16],"is":[17],"an":[18,29,106],"illustrative":[19],"example":[20],"that":[21,45,98,143],"generates":[22],"abstract":[23],"representations":[24],"of":[25,51,77,108,127,136,146,156],"tokens":[26,37],"inputted":[27],"to":[28,35,63,119],"encoder":[30],"based":[31],"on":[32,113,133,153],"their":[33,70],"relationships":[34],"all":[36],"a":[39,124,134,154],"sequence.":[40],"Recent":[41],"studies":[42],"although":[46],"such":[47,92],"are":[49],"capable":[50],"learning":[52,65],"syntactic":[53,73],"features":[54,104],"purely":[55],"by":[56],"seeing":[57],"examples,":[58],"explicitly":[59],"feeding":[60],"this":[61],"information":[62,74],"deep":[64],"can":[67],"significantly":[68],"enhance":[69],"performance.":[71],"Leveraging":[72],"like":[75],"part":[76],"speech":[78],"(POS)":[79],"may":[80],"be":[81],"particularly":[82],"beneficial":[83],"limited":[85],"training":[86],"data":[87],"settings":[88],"complex":[90],"as":[93],"the":[94,99,114,137,144,160],"Transformer.":[95],"We":[96],"show":[97],"syntax-infused":[100],"Transformer":[101],"with":[102],"multiple":[103],"achieves":[105],"0.7":[109],"BLEU":[110,129],"when":[111,131],"trained":[112,132],"full":[115],"WMT":[116],"14":[117],"English":[118],"German":[120],"translation":[121],"dataset":[122],"and":[123],"maximum":[125],"1.99":[128],"points":[130],"fraction":[135],"dataset.":[138],"In":[139],"addition,":[140],"we":[141],"find":[142],"incorporation":[145],"syntax":[147],"into":[148],"BERT":[149],"fine-tuning":[150],"outperforms":[151],"baseline":[152],"number":[155],"downstream":[157],"tasks":[158],"from":[159],"GLUE":[161],"benchmark.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-11-22T00:00:00"}