{"id":"https://openalex.org/W2963737810","doi":"https://doi.org/10.1162/tacl_a_00113","title":"The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages","display_name":"The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2963737810","doi":"https://doi.org/10.1162/tacl_a_00113","mag":"2963737810"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00113","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00113","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00113","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00113","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043674345","display_name":"Dingquan Wang","orcid":"https://orcid.org/0000-0003-2055-6711"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dingquan Wang","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052467896","display_name":"Jason Eisner","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason Eisner","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University,","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043674345","https://openalex.org/A5052467896"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":11.6936,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.9848573,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"4","issue":null,"first_page":"491","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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/T10260","display_name":"Software Engineering Research","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/treebank","display_name":"Treebank","score":0.9045122861862183},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8895825147628784},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7126098871231079},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7118974328041077},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6501979231834412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6430261731147766},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4781123995780945},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.4754488170146942},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.23335763812065125},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16961669921875}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9045122861862183},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8895825147628784},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7126098871231079},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7118974328041077},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6501979231834412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6430261731147766},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4781123995780945},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.4754488170146942},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.23335763812065125},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16961669921875},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00113","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00113","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00113","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ae62b018fd4144708bc3504b610fa85f","is_oa":false,"landing_page_url":"https://doaj.org/article/ae62b018fd4144708bc3504b610fa85f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 4 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00113","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00113","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00113","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963737810.pdf","grobid_xml":"https://content.openalex.org/works/W2963737810.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W146688011","https://openalex.org/W803770162","https://openalex.org/W1544827683","https://openalex.org/W1544916875","https://openalex.org/W1605758875","https://openalex.org/W1615927100","https://openalex.org/W1762961584","https://openalex.org/W1841959837","https://openalex.org/W1894835849","https://openalex.org/W1908676432","https://openalex.org/W1970652161","https://openalex.org/W1979651826","https://openalex.org/W2050034390","https://openalex.org/W2089683596","https://openalex.org/W2099621636","https://openalex.org/W2114609248","https://openalex.org/W2140146712","https://openalex.org/W2140721185","https://openalex.org/W2153568660","https://openalex.org/W2154368244","https://openalex.org/W2156163116","https://openalex.org/W2161795601","https://openalex.org/W2162245945","https://openalex.org/W2164076936","https://openalex.org/W2165921245","https://openalex.org/W2230677025","https://openalex.org/W2250313959","https://openalex.org/W2250520759","https://openalex.org/W2250741688","https://openalex.org/W2251957808","https://openalex.org/W2251994480","https://openalex.org/W2518150831","https://openalex.org/W2962790689","https://openalex.org/W3088675891","https://openalex.org/W4242599633"],"related_works":["https://openalex.org/W4301800915","https://openalex.org/W2739034105","https://openalex.org/W2963839582","https://openalex.org/W2964047924","https://openalex.org/W2743945814","https://openalex.org/W4299838440","https://openalex.org/W2962832505","https://openalex.org/W1043255351","https://openalex.org/W2135057643","https://openalex.org/W1533278948"],"abstract_inverted_index":{"We":[0,67,111],"release":[1],"Galactic":[2,88],"Dependencies":[3,18],"1.0\u2014a":[4],"large":[5],"set":[6],"of":[7,54,63,76,84,87,122],"synthetic":[8,41,78,115],"languages":[9,117],"not":[10],"found":[11],"on":[12,106],"Earth,":[13],"but":[14],"annotated":[15],"in":[16],"Universal":[17],"format.":[19],"This":[20],"new":[21],"resource":[22],"aims":[23],"to":[24,35,37,58,96],"provide":[25],"training":[26],"and":[27,74],"development":[28],"data":[29],"for":[30,130],"NLP":[31],"methods":[32],"that":[33,113],"aim":[34],"adapt":[36],"unfamiliar":[38],"languages.":[39,66,79,133],"Each":[40],"treebank":[42,48],"is":[43],"produced":[44],"from":[45],"a":[46,81,98,103,107],"real":[47,65,99],"by":[49],"stochastically":[50],"permuting":[51],"the":[52,60,69,77,85,120,123],"dependents":[53],"nouns":[55],"and/or":[56],"verbs":[57],"match":[59],"word":[61],"order":[62],"other":[64],"discuss":[68],"usefulness,":[70],"realism,":[71],"parsability,":[72],"perplexity,":[73],"diversity":[75,121],"As":[80],"simple":[82],"demonstration":[83],"use":[86],"Dependencies,":[89],"we":[90],"consider":[91],"single-source":[92],"transfer,":[93],"which":[94,126],"attempts":[95],"parse":[97],"target":[100,132],"language":[101],"using":[102],"parser":[104],"trained":[105],"\u201cnearby\u201d":[108],"source":[109,116,124],"language.":[110],"find":[112],"including":[114],"somewhat":[118],"increases":[119],"pool,":[125],"significantly":[127],"improves":[128],"results":[129],"most":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}