{"id":"https://openalex.org/W2963643701","doi":"https://doi.org/10.18653/v1/p19-1340","title":"Multilingual Constituency Parsing with Self-Attention and Pre-Training","display_name":"Multilingual Constituency Parsing with Self-Attention and Pre-Training","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2963643701","doi":"https://doi.org/10.18653/v1/p19-1340","mag":"2963643701"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1340","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1340","pdf_url":"https://www.aclweb.org/anthology/P19-1340.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1340.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011843361","display_name":"Nikita Kitaev","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nikita Kitaev","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004414481","display_name":"Steven Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Cao","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Klein","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011843361"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":20.5455,"has_fulltext":true,"cited_by_count":212,"citation_normalized_percentile":{"value":0.99488027,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3499","last_page":"3505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8394110798835754},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6577580571174622},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5842074751853943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5831226706504822},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5560071468353271},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5479656457901001},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5377370119094849},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.48704198002815247},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4547105133533478},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4290406107902527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394110798835754},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6577580571174622},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5842074751853943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831226706504822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5560071468353271},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5479656457901001},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5377370119094849},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.48704198002815247},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4547105133533478},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4290406107902527},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1340","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1340","pdf_url":"https://www.aclweb.org/anthology/P19-1340.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1340","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1340","pdf_url":"https://www.aclweb.org/anthology/P19-1340.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963643701.pdf","grobid_xml":"https://content.openalex.org/works/W2963643701.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W759515131","https://openalex.org/W2098021339","https://openalex.org/W2143391265","https://openalex.org/W2493916176","https://openalex.org/W2564486991","https://openalex.org/W2739769945","https://openalex.org/W2849665241","https://openalex.org/W2896457183","https://openalex.org/W2962690139","https://openalex.org/W2962739339","https://openalex.org/W2962772361","https://openalex.org/W2963026768","https://openalex.org/W2963033685","https://openalex.org/W2963073938","https://openalex.org/W2963084773","https://openalex.org/W2963227939","https://openalex.org/W2963372751","https://openalex.org/W2963462075","https://openalex.org/W4294367149"],"related_works":["https://openalex.org/W2502722637","https://openalex.org/W2167662847","https://openalex.org/W1551406738","https://openalex.org/W2351267244","https://openalex.org/W2369308426","https://openalex.org/W2293457016","https://openalex.org/W2977842567","https://openalex.org/W1590308178","https://openalex.org/W2789919619","https://openalex.org/W1818857488"],"abstract_inverted_index":{"We":[0,20,29,111],"show":[1,66,120],"that":[2,32,67,121],"constituency":[3],"parsing":[4],"benefits":[5,24],"from":[6,130],"unsupervised":[7],"pre-training":[8,18,33,70],"across":[9,36],"a":[10,15,77,104,126],"variety":[11],"of":[12,17,25,80,116,134],"languages":[13,39,84,125],"and":[14,71,119,150],"range":[16],"conditions.":[19],"first":[21],"compare":[22],"the":[23,86,114,131],"no":[26],"pre-training,":[27],"fastText":[28],"also":[30],"find":[31],"is":[34],"beneficial":[35],"all":[37,75],"11":[38,144],"tested;":[40],"however,":[41],"large":[42],"model":[43,93,99],"sizes":[44],"(more":[45],"than":[46],"100":[47],"million":[48],"parameters)":[49],"make":[50],"it":[51,122],"computationally":[52],"expensive":[53],"to":[54,96,128],"train":[55],"separate":[56],"models":[57],"for":[58,143],"each":[59],"language.":[60],"To":[61],"address":[62],"this":[63],"shortcoming,":[64],"we":[65,138],"joint":[68,117],"multilingual":[69],"fine-tuning":[72,97,118],"allows":[73],"sharing":[74],"but":[76],"small":[78],"number":[79],"parameters":[81],"between":[82],"ten":[83],"in":[85,92,109],"final":[87],"model.":[88],"The":[89],"10x":[90],"reduction":[91],"size":[94],"compared":[95],"one":[98],"per":[100],"language":[101],"causes":[102],"only":[103],"3.2%":[105],"relative":[106],"error":[107],"increase":[108],"aggregate.":[110],"further":[112],"explore":[113],"idea":[115],"gives":[123],"low-resource":[124],"way":[127],"benefit":[129],"larger":[132],"datasets":[133],"other":[135],"languages.":[136],"Finally,":[137],"demonstrate":[139],"new":[140],"state-ofthe-art":[141],"results":[142],"languages,":[145],"including":[146],"English":[147],"(95.8":[148],"F1)":[149],"Chinese":[151],"(91.8":[152],"F1).":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":41},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":24}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}