{"id":"https://openalex.org/W2949399460","doi":"https://doi.org/10.18653/v1/p19-1235","title":"Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction","display_name":"Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949399460","doi":"https://doi.org/10.18653/v1/p19-1235","mag":"2949399460"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1235","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1235","pdf_url":"https://www.aclweb.org/anthology/P19-1235.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1235.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013847092","display_name":"Lifeng Jin","orcid":"https://orcid.org/0000-0002-6754-7014"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lifeng Jin","raw_affiliation_strings":["Department of Linguistics The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086362177","display_name":"William Schuler","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Schuler","raw_affiliation_strings":["Department of Linguistics The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013847092"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.4335,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71272463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2453","last_page":"2463"},"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":0.9995999932289124,"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":0.9980999827384949,"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":0.7151373028755188},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6712279319763184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6570568084716797},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6468650698661804},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5683790445327759},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.47217220067977905},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4425014555454254},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18771815299987793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151373028755188},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6712279319763184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6570568084716797},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6468650698661804},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5683790445327759},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.47217220067977905},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4425014555454254},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18771815299987793},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1235","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1235","pdf_url":"https://www.aclweb.org/anthology/P19-1235.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/p19-1235","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1235","pdf_url":"https://www.aclweb.org/anthology/P19-1235.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":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1125141860","display_name":null,"funder_award_id":"1816891","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"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"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949399460.pdf","grobid_xml":"https://content.openalex.org/works/W2949399460.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W82889912","https://openalex.org/W328458486","https://openalex.org/W1495446613","https://openalex.org/W1632114991","https://openalex.org/W2022724901","https://openalex.org/W2088672056","https://openalex.org/W2089683596","https://openalex.org/W2093483153","https://openalex.org/W2100249433","https://openalex.org/W2100750861","https://openalex.org/W2102872690","https://openalex.org/W2102910670","https://openalex.org/W2115803233","https://openalex.org/W2116716943","https://openalex.org/W2117823388","https://openalex.org/W2157365695","https://openalex.org/W2163176220","https://openalex.org/W2164151151","https://openalex.org/W2166451556","https://openalex.org/W2170716495","https://openalex.org/W2182841334","https://openalex.org/W2197719701","https://openalex.org/W2334424438","https://openalex.org/W2493232835","https://openalex.org/W2563157576","https://openalex.org/W2573665311","https://openalex.org/W2579343286","https://openalex.org/W2595406588","https://openalex.org/W2740840489","https://openalex.org/W2890487939","https://openalex.org/W2963525616","https://openalex.org/W2963754491","https://openalex.org/W3103362336","https://openalex.org/W4296300796","https://openalex.org/W4302556686"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W2392917763","https://openalex.org/W2083429127","https://openalex.org/W2358855848","https://openalex.org/W2142145894","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830"],"abstract_inverted_index":{"In":[0,22],"unsupervised":[1],"grammar":[2,48],"induction,":[3],"data":[4,51,67,75,95],"likelihood":[5,76,96],"is":[6],"known":[7],"to":[8,24,41,89,108,120],"be":[9,90],"only":[10],"weakly":[11],"correlated":[12],"with":[13,63,124,134],"parsing":[14,42,64],"accuracy,":[15],"especially":[16],"at":[17],"convergence":[18],"after":[19],"multiple":[20],"runs.":[21],"order":[23,100],"find":[25],"a":[26,45,81,91],"better":[27,61,92,121],"indicator":[28],"for":[29,77,97],"quality":[30],"of":[31,57,74],"induced":[32],"grammars,":[33,118],"this":[34],"paper":[35],"correlates":[36,62],"several":[37],"linguistically-and":[38],"psycholinguisticallymotivated":[39],"predictors":[40],"accuracy":[43,65,83],"on":[44],"large":[46],"multilingual":[47],"induction":[49],"evaluation":[50],"set.":[52],"Results":[53],"show":[54,104],"that":[55,70,105,130],"variance":[56],"average":[58],"surprisal":[59],"(VAS)":[60],"than":[66,94],"likelihood,":[68],"and":[69,119],"using":[71],"VAS":[72,88,106],"instead":[73],"model":[78],"selection":[79],"provides":[80],"significant":[82],"boost.":[84],"Further":[85],"evidence":[86],"shows":[87],"candidate":[93],"predicting":[98],"word":[99],"typology":[101],"classification.":[102],"Analyses":[103],"seems":[107],"separate":[109,128],"content":[110],"words":[111,114,123],"from":[112],"function":[113],"in":[115],"natural":[116],"language":[117],"arrange":[122],"different":[125],"frequencies":[126],"into":[127],"classes":[129],"are":[131],"more":[132],"consistent":[133],"linguistic":[135],"theory.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}