{"id":"https://openalex.org/W4389777835","doi":"https://doi.org/10.1162/tacl_a_00612","title":"Testing the Predictions of Surprisal Theory in 11 Languages","display_name":"Testing the Predictions of Surprisal Theory in 11 Languages","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389777835","doi":"https://doi.org/10.1162/tacl_a_00612"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00612","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00612","pdf_url":null,"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":"https://doi.org/10.1162/tacl_a_00612","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021124394","display_name":"Ethan G. Wilcox","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Ethan G. Wilcox","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland. ethan.wilcox@inf.ethz.ch"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland. ethan.wilcox@inf.ethz.ch","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102825308","display_name":"Tiago Pimentel","orcid":"https://orcid.org/0000-0002-5159-4641"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tiago Pimentel","raw_affiliation_strings":["University of Cambridge, UK. tp472@cam.ac.uk"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, UK. tp472@cam.ac.uk","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029033876","display_name":"Clara Meister","orcid":"https://orcid.org/0000-0002-3775-4426"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Clara Meister","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland. clara.meister@inf.ethz.ch"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland. clara.meister@inf.ethz.ch","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061951606","display_name":"Ryan Cotterell","orcid":"https://orcid.org/0000-0003-4080-1833"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ryan Cotterell","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland. ryan.cotterell@inf.ethz.ch"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland. ryan.cotterell@inf.ethz.ch","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090215557","display_name":"Roger L\u00e9vy","orcid":"https://orcid.org/0000-0002-4493-8864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roger P. Levy","raw_affiliation_strings":["MIT, USA. rplevy@mit.edu"],"affiliations":[{"raw_affiliation_string":"MIT, USA. rplevy@mit.edu","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021124394"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":10.6257,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.99063371,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"11","issue":null,"first_page":"1451","last_page":"1470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9984999895095825,"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":0.9977999925613403,"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":0.7363241314888},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5602120161056519},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49775436520576477},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4806765019893646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46029648184776306},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43907830119132996},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.43422698974609375},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4125673770904541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7363241314888},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5602120161056519},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49775436520576477},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4806765019893646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46029648184776306},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43907830119132996},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43422698974609375},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4125673770904541},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00612","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00612","pdf_url":null,"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:69881e4ba7624ca3951ae67454fa5e38","is_oa":true,"landing_page_url":"https://doaj.org/article/69881e4ba7624ca3951ae67454fa5e38","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 11 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00612","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00612","pdf_url":null,"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":[{"display_name":"Quality Education","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2133986208","display_name":null,"funder_award_id":"2121074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6861016552","display_name":null,"funder_award_id":"BCS-2121074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","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/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W9489473","https://openalex.org/W107090387","https://openalex.org/W1816291044","https://openalex.org/W1976046848","https://openalex.org/W1995875735","https://openalex.org/W2013112874","https://openalex.org/W2026356512","https://openalex.org/W2053374418","https://openalex.org/W2054125330","https://openalex.org/W2067575282","https://openalex.org/W2075494153","https://openalex.org/W2108010971","https://openalex.org/W2118276816","https://openalex.org/W2129056111","https://openalex.org/W2139450036","https://openalex.org/W2141845152","https://openalex.org/W2156545345","https://openalex.org/W2157365695","https://openalex.org/W2164418233","https://openalex.org/W2166624585","https://openalex.org/W2178225550","https://openalex.org/W2564663642","https://openalex.org/W2594908799","https://openalex.org/W2616278914","https://openalex.org/W2786354489","https://openalex.org/W2795342569","https://openalex.org/W2803214681","https://openalex.org/W2933138175","https://openalex.org/W2953092638","https://openalex.org/W2954933613","https://openalex.org/W2963341956","https://openalex.org/W2963979492","https://openalex.org/W2971775690","https://openalex.org/W2979736636","https://openalex.org/W2995543961","https://openalex.org/W3035390927","https://openalex.org/W3087624537","https://openalex.org/W3171355829","https://openalex.org/W3174658628","https://openalex.org/W3175306105","https://openalex.org/W3176198948","https://openalex.org/W3213249206","https://openalex.org/W4205537173","https://openalex.org/W4210813972","https://openalex.org/W4224247062","https://openalex.org/W4231242566","https://openalex.org/W4251108623","https://openalex.org/W4282967944","https://openalex.org/W4287993739","https://openalex.org/W4288089799","https://openalex.org/W4298742451","https://openalex.org/W4299613993","https://openalex.org/W4306964455","https://openalex.org/W4309994492","https://openalex.org/W4319915529","https://openalex.org/W4361766487","https://openalex.org/W4385573487","https://openalex.org/W4389777845","https://openalex.org/W4404783274","https://openalex.org/W4404783355","https://openalex.org/W6604373762","https://openalex.org/W6631190155","https://openalex.org/W6681860728","https://openalex.org/W6732615037","https://openalex.org/W6769627184","https://openalex.org/W6771823989","https://openalex.org/W6775150526","https://openalex.org/W6775301884","https://openalex.org/W6779016856","https://openalex.org/W6798387921","https://openalex.org/W6810252847"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2060629350","https://openalex.org/W2349302580","https://openalex.org/W2390154576","https://openalex.org/W2082438799","https://openalex.org/W1966986837"],"abstract_inverted_index":{"Abstract":[0],"Surprisal":[1],"theory":[2,32,172],"posits":[3],"that":[4,141,160],"less-predictable":[5],"words":[6],"should":[7],"take":[8],"more":[9,153],"time":[10],"to":[11,168],"process,":[12],"with":[13,103],"word":[14],"predictability":[15],"quantified":[16],"as":[17],"surprisal,":[18,117],"i.e.,":[19,118],"negative":[20],"log":[21],"probability":[22],"in":[23,65,78],"context.":[24],"While":[25],"evidence":[26],"supporting":[27],"the":[28,66,71,129,164],"predictions":[29,101,144],"of":[30,38,47,111,123,156],"surprisal":[31,74,104,108,133],"has":[33,40],"been":[34],"replicated":[35],"widely,":[36],"much":[37],"it":[39],"focused":[41],"on":[42,93,151],"a":[43,152],"very":[44],"narrow":[45],"slice":[46],"data:":[48],"native":[49],"English":[50,53],"speakers":[51],"reading":[52,76,112,124,135],"texts.":[54],"Indeed,":[55],"no":[56],"comprehensive":[57],"multilingual":[58,96],"analysis":[59],"exists.":[60],"We":[61,139],"address":[62],"this":[63],"gap":[64],"current":[67],"literature":[68],"by":[69],"investigating":[70],"relationship":[72],"between":[73,132,170],"and":[75,95,126,134,173],"times":[77,136],"eleven":[79],"different":[80],"languages,":[81,157],"distributed":[82],"across":[83,177],"five":[84],"language":[85,90,175],"families.":[86],"Deriving":[87],"estimates":[88],"from":[89],"models":[91],"trained":[92],"monolingual":[94],"corpora,":[97],"we":[98,158],"test":[99],"three":[100,143],"associated":[102],"theory:":[105],"(i)":[106],"whether":[107,115,128],"is":[109,121,137],"predictive":[110,122],"times,":[113,125],"(ii)":[114],"expected":[116],"contextual":[119],"entropy,":[120],"(iii)":[127],"linking":[130],"function":[131],"linear.":[138],"find":[140],"all":[142],"are":[145],"borne":[146],"out":[147],"crosslinguistically.":[148],"By":[149],"focusing":[150],"diverse":[154],"set":[155],"argue":[159],"these":[161],"results":[162],"offer":[163],"most":[165],"robust":[166],"link":[167],"date":[169],"information":[171],"incremental":[174],"processing":[176],"languages.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}