{"id":"https://openalex.org/W4389519307","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.128","title":"Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens","display_name":"Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389519307","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.128"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.128","pdf_url":"https://aclanthology.org/2023.findings-emnlp.128.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-emnlp.128.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066248885","display_name":"Byung-Doh Oh","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":"Byung-Doh Oh","raw_affiliation_strings":["Department of Linguistics The Ohio State University"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics The Ohio State University","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":true,"raw_author_name":"William Schuler","raw_affiliation_strings":["Department of Linguistics The Ohio State University"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086362177"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.8843,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88813555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1915","last_page":"1921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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/T13629","display_name":"Text Readability and Simplification","score":0.9871000051498413,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9456999897956848,"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/perplexity","display_name":"Perplexity","score":0.9045259952545166},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.797310471534729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367368340492249},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7098182439804077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49875497817993164},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49809932708740234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3471566140651703}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9045259952545166},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.797310471534729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367368340492249},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7098182439804077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49875497817993164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49809932708740234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3471566140651703},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.128","pdf_url":"https://aclanthology.org/2023.findings-emnlp.128.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.128","pdf_url":"https://aclanthology.org/2023.findings-emnlp.128.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"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"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389519307.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1951724000","https://openalex.org/W1995875735","https://openalex.org/W2054125330","https://openalex.org/W2108010971","https://openalex.org/W2139450036","https://openalex.org/W2164418233","https://openalex.org/W2795342569","https://openalex.org/W2962784628","https://openalex.org/W2962941914","https://openalex.org/W2964531451","https://openalex.org/W2997938465","https://openalex.org/W3033254023","https://openalex.org/W3083146265","https://openalex.org/W3118781290","https://openalex.org/W3171953676","https://openalex.org/W4214909510","https://openalex.org/W4281758439","https://openalex.org/W4309994492","https://openalex.org/W4361766487","https://openalex.org/W4362655426","https://openalex.org/W4385572280","https://openalex.org/W4385573487"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3049463507"],"abstract_inverted_index":{"Recent":[0],"psycholinguistic":[1],"studies":[2],"have":[3],"drawn":[4],"conflicting":[5],"conclusions":[6],"about":[7,108],"the":[8,11,18,37,42,73,103,135,155,165],"relationship":[9],"between":[10],"quality":[12],"of":[13,20,44,75,158,181],"a":[14,128,178],"language":[15,66,138,174,188],"model":[16,48,67,79,100,125,139,182],"and":[17,47,78,176],"ability":[19,83],"its":[21],"surprisal":[22,62,93,170],"estimates":[23,63,94],"to":[24,33,36,56,84,117,142,147,190],"predict":[25,85],"human":[26,86,148],"reading":[27,87,149],"times,":[28],"which":[29,114,134],"has":[30],"been":[31],"speculated":[32],"be":[34],"due":[35],"large":[38],"gap":[39],"in":[40,72,137,144],"both":[41],"amount":[43,74,157],"training":[45,76,111,159],"data":[46,77,160],"capacity":[49,80,183],"across":[50],"studies.":[51],"The":[52,89],"current":[53],"work":[54],"aims":[55],"consolidate":[57],"these":[58],"findings":[59],"by":[60,169],"evaluating":[61],"from":[64,95,119,171],"Transformer-based":[65,187],"variants":[68,97,126],"that":[69,92,154,177],"vary":[70],"systematically":[71],"on":[81],"their":[82],"times.":[88,150],"results":[90,152],"show":[91],"most":[96],"with":[98],"contemporary":[99],"capacities":[101],"provide":[102],"best":[104],"fit":[105,167],"after":[106,113,133],"seeing":[107],"two":[109],"billion":[110],"tokens,":[112],"they":[115],"begin":[116],"diverge":[118],"humanlike":[120,192],"expectations.":[121,193],"Additionally,":[122],"newly-trained":[123],"smaller":[124],"reveal":[127],"'tipping":[129],"point'":[130],"at":[131],"convergence,":[132],"decrease":[136],"perplexity":[140],"begins":[141],"result":[143],"poorer":[145,166],"fits":[146],"These":[151],"suggest":[153],"massive":[156],"is":[161,184],"mainly":[162],"responsible":[163],"for":[164,186],"achieved":[168],"larger":[172],"pre-trained":[173],"models,":[175],"certain":[179],"degree":[180],"necessary":[185],"models":[189],"capture":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}