{"id":"https://openalex.org/W3104633006","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.389","title":"Unsupervised Parsing via Constituency Tests","display_name":"Unsupervised Parsing via Constituency Tests","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3104633006","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.389","mag":"3104633006"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.emnlp-main.389","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.389","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.389.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.emnlp-main.389.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004414481","display_name":"Steven Cao","orcid":"https://orcid.org/0000-0003-0476-1520"},"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"],"raw_orcid":null,"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/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":false,"raw_author_name":"Nikita Kitaev","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"raw_orcid":null,"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.4149,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91499547,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4798","last_page":"4808"},"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955000281333923,"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/grammaticality","display_name":"Grammaticality","score":0.9874009490013123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8153781890869141},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.797408938407898},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7458299398422241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7165660262107849},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6685183048248291},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6671713590621948},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5951164364814758},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5624969005584717},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5100803971290588},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.18080750107765198},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17552676796913147},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1257341504096985},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10453370213508606}],"concepts":[{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.9874009490013123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153781890869141},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.797408938407898},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7458299398422241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7165660262107849},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6685183048248291},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6671713590621948},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5951164364814758},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5624969005584717},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5100803971290588},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.18080750107765198},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17552676796913147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1257341504096985},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10453370213508606},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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:10.18653/v1/2020.emnlp-main.389","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.389","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.389.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.emnlp-main.389","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.389","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.389.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G3128219423","display_name":"RI: Small: Collaborative Research: Unsupervised Transcription of Early Modern Documents","funder_award_id":"1618460","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3104633006.pdf","grobid_xml":"https://content.openalex.org/works/W3104633006.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1495446613","https://openalex.org/W1522301498","https://openalex.org/W1632114991","https://openalex.org/W2107419438","https://openalex.org/W2113075298","https://openalex.org/W2129882630","https://openalex.org/W2137143056","https://openalex.org/W2165405828","https://openalex.org/W2531882892","https://openalex.org/W2932376173","https://openalex.org/W2932637973","https://openalex.org/W2949399644","https://openalex.org/W2963033685","https://openalex.org/W2963073938","https://openalex.org/W2963084773","https://openalex.org/W2963341956","https://openalex.org/W2963411763","https://openalex.org/W2963754491","https://openalex.org/W2964030814","https://openalex.org/W2964121744","https://openalex.org/W2965373594","https://openalex.org/W2978670439","https://openalex.org/W2995856824","https://openalex.org/W3004117589","https://openalex.org/W4289373464"],"related_works":["https://openalex.org/W1043255351","https://openalex.org/W2135057643","https://openalex.org/W1533278948","https://openalex.org/W1781980207","https://openalex.org/W2109902858","https://openalex.org/W2951759144","https://openalex.org/W28706907","https://openalex.org/W2949524199","https://openalex.org/W2104399512","https://openalex.org/W3101476433"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,13,33,57,74,77,122],"method":[3],"for":[4],"unsupervised":[5,53,64],"parsing":[6],"based":[7],"on":[8,144],"the":[9,23,30,38,92,96,107,118,130,135,145,157],"linguistic":[10],"notion":[11],"of":[12,18,59,109,153],"constituency":[14,19,86],"test.":[15],"One":[16],"type":[17],"test":[20,87,148],"involves":[21],"modifying":[22],"sentence":[24],"via":[25],"some":[26],"transformation":[27],"(e.g.":[28,40],"replacing":[29],"span":[31,82],"with":[32,95],"pronoun)":[34],"and":[35,61,89,133],"then":[36],"judging":[37],"result":[39],"checking":[41],"if":[42],"it":[43],"is":[44],"grammatical).":[45],"Motivated":[46],"by":[47,55,83,116],"this":[48,101],"idea,":[49],"we":[50,79,90,112,126],"design":[51],"an":[52,63,150],"parser":[54],"specifying":[56],"set":[58],"transformations":[60],"using":[62],"neural":[65],"acceptability":[66],"model":[67,120,140],"to":[68],"make":[69],"grammaticality":[70,119,136],"decisions.":[71],"To":[72],"produce":[73],"tree":[75,94],"given":[76],"sentence,":[78],"score":[80],"each":[81],"aggregating":[84],"its":[85],"judgments,":[88],"choose":[91],"binary":[93],"highest":[97],"total":[98],"score.":[99],"While":[100],"approach":[102],"already":[103],"achieves":[104,141],"performance":[105],"in":[106],"range":[108],"current":[110],"methods,":[111],"further":[113],"improve":[114],"accuracy":[115],"fine-tuning":[117],"through":[121],"refinement":[123],"procedure,":[124],"where":[125],"alternate":[127],"between":[128],"improving":[129,134],"estimated":[131],"trees":[132],"model.":[137],"The":[138],"refined":[139],"62.8":[142],"F1":[143],"Penn":[146],"Treebank":[147],"set,":[149],"absolute":[151],"improvement":[152],"7.6":[154],"points":[155],"over":[156],"previous":[158],"best":[159],"published":[160],"result.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":13}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}