{"id":"https://openalex.org/W7140087572","doi":"https://doi.org/10.18653/v1/2026.sigtyp-main.4","title":"What does Surprisal have to do with Information Status?","display_name":"What does Surprisal have to do with Information Status?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140087572","doi":"https://doi.org/10.18653/v1/2026.sigtyp-main.4"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.sigtyp-main.4","doi":"https://doi.org/10.18653/v1/2026.sigtyp-main.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigtyp-main.4","pdf_url":"https://aclanthology.org/2026.sigtyp-main.4.pdf","source":{"id":"https://openalex.org/S7407106814","display_name":"Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"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 8th Workshop on Research in Computational Linguistic Typology and Multilingual NLP","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.sigtyp-main.4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108862487","display_name":"Andrew Thomas Dyer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andrew Thomas Dyer","raw_affiliation_strings":["Language Science and Technology Saarland University , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Science and Technology Saarland University , Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108862487"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11817401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.5102999806404114,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.5102999806404114,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.28200000524520874,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.06260000169277191,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/information-status","display_name":"information status","score":0.9789999723434448},{"id":"https://openalex.org/keywords/information-structure","display_name":"information structure","score":0.9259999990463257},{"id":"https://openalex.org/keywords/novelty","display_name":"novelty","score":0.4740000069141388},{"id":"https://openalex.org/keywords/parts-of-speech","display_name":"parts of speech","score":0.847000002861023},{"id":"https://openalex.org/keywords/word-frequency","display_name":"word frequency","score":0.9980000257492065},{"id":"https://openalex.org/keywords/language-production","display_name":"language production","score":0.7059999704360962},{"id":"https://openalex.org/keywords/information-content","display_name":"information content","score":0.43700000643730164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4616999924182892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3968999981880188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2281000018119812},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.22419999539852142},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.22210000455379486}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.sigtyp-main.4","doi":"https://doi.org/10.18653/v1/2026.sigtyp-main.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigtyp-main.4","pdf_url":"https://aclanthology.org/2026.sigtyp-main.4.pdf","source":{"id":"https://openalex.org/S7407106814","display_name":"Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"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 8th Workshop on Research in Computational Linguistic Typology and Multilingual NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.sigtyp-main.4","doi":"https://doi.org/10.18653/v1/2026.sigtyp-main.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigtyp-main.4","pdf_url":"https://aclanthology.org/2026.sigtyp-main.4.pdf","source":{"id":"https://openalex.org/S7407106814","display_name":"Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"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 8th Workshop on Research in Computational Linguistic Typology and Multilingual NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Reduced inequalities","score":0.43523111939430237,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1951765764","display_name":null,"funder_award_id":"SFB 1102","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G737504480","display_name":"SFB 1102: Informationsdichte und sprachliche Kodierung","funder_award_id":"232722074","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140087572.pdf","grobid_xml":"https://content.openalex.org/works/W7140087572.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7162643409","https://openalex.org/W4407838491","https://openalex.org/W2795342569","https://openalex.org/W7130279031","https://openalex.org/W4404782569","https://openalex.org/W7036975600","https://openalex.org/W6922400300","https://openalex.org/W7166827824","https://openalex.org/W7160727157","https://openalex.org/W7166569301"],"abstract_inverted_index":{"It":[0],"is":[1,26,63,73,89,109],"common":[2],"in":[3,21],"cognitive":[4],"computational":[5],"linguistics":[6],"to":[7,28,32,40,46,69],"use":[8],"language":[9,22],"model":[10],"surprisal":[11,72,120,148],"as":[12,80,97,153],"a":[13,52,112,154],"measure":[14],"of":[15,19,56,99,116,129,131,157],"the":[16,127],"information":[17,33,57,78,95,106,139,158],"content":[18],"units":[20],"production.From":[23],"here,":[24],"it":[25],"tempting":[27],"then":[29],"apply":[30],"this":[31,61,87],"structure":[34],"and":[35,43,83,101,118,141,143],"status,":[36],"considering":[37],"surprising":[38],"mentions":[39],"be":[41,47,122,151],"new":[42],"unsurprising":[44],"ones":[45],"given,":[48],"providing":[49],"us":[50],"with":[51,137],"ready-made":[53],"continuous":[54,155],"metric":[55],"givenness/newness.To":[58],"see":[59,70],"if":[60,71,84,86],"conflation":[62],"appropriate,":[64],"we":[65],"perform":[66],"regression":[67],"experiments":[68],"actually":[74],"well":[75],"predicted":[76,125],"by":[77,126,160],"status":[79,107,140,159],"manually":[81],"annotated,":[82],"so,":[85],"effect":[88,128],"separable":[90],"from":[91],"more":[92],"trivial":[93],"linguistic":[94],"such":[96],"parts":[98,130],"speech":[100],"word":[102,144],"frequency.We":[103,145],"find":[104],"that":[105,119,147],"alone":[108],"at":[110],"best":[111],"very":[113],"weak":[114],"predictor":[115],"surprisal,":[117],"can":[121],"much":[123],"better":[124],"speech,":[132],"which":[133],"are":[134],"highly":[135],"correlated":[136],"both":[138],"surprisal;":[142],"conclude":[146],"should":[149],"not":[150],"used":[152],"representation":[156],"itself.":[161]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}
