{"id":"https://openalex.org/W3001772156","doi":"https://doi.org/10.1162/tacl_a_00296","title":"Phonotactic Complexity and Its Trade-offs","display_name":"Phonotactic Complexity and Its Trade-offs","publication_year":2020,"publication_date":"2020-01-23","ids":{"openalex":"https://openalex.org/W3001772156","doi":"https://doi.org/10.1162/tacl_a_00296","mag":"3001772156"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00296","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00296","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00296/1923388/tacl_a_00296.pdf","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":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00296/1923388/tacl_a_00296.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tiago Pimentel","orcid":null},"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":true,"raw_author_name":"Tiago Pimentel","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Brian Roark","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Roark","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ryan Cotterell","orcid":null},"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":"Ryan Cotterell","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":90.5194,"has_fulltext":true,"cited_by_count":58,"citation_normalized_percentile":{"value":0.99963725,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.36959999799728394,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.36959999799728394,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.3296999931335449,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.03400000184774399,"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/phonotactics","display_name":"Phonotactics","score":0.9495999813079834},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6485000252723694},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6230999827384949},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4909000098705292},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4375999867916107},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3273000121116638},{"id":"https://openalex.org/keywords/word-length","display_name":"Word length","score":0.3188999891281128}],"concepts":[{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.9495999813079834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458999752998352},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6485000252723694},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4909000098705292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4440000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44179999828338623},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C3019641298","wikidata":"https://www.wikidata.org/wiki/Q625642","display_name":"Word length","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/tacl_a_00296","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00296","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00296/1923388/tacl_a_00296.pdf","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:arXiv.org:2005.03774","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.03774","pdf_url":"https://arxiv.org/pdf/2005.03774","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:947852ef831b483fa5eb29a65f0d4dce","is_oa":true,"landing_page_url":"https://doaj.org/article/947852ef831b483fa5eb29a65f0d4dce","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 8, Pp 1-18 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00296","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00296","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00296/1923388/tacl_a_00296.pdf","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3001772156.pdf","grobid_xml":"https://content.openalex.org/works/W3001772156.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W611137783","https://openalex.org/W1780831889","https://openalex.org/W1969762243","https://openalex.org/W1974558812","https://openalex.org/W1993507215","https://openalex.org/W1996056154","https://openalex.org/W2022564164","https://openalex.org/W2026356512","https://openalex.org/W2031505338","https://openalex.org/W2035306329","https://openalex.org/W2039710284","https://openalex.org/W2041333862","https://openalex.org/W2055563597","https://openalex.org/W2064675550","https://openalex.org/W2083804014","https://openalex.org/W2118004980","https://openalex.org/W2120321299","https://openalex.org/W2126110252","https://openalex.org/W2131154351","https://openalex.org/W2164418233","https://openalex.org/W2483562713","https://openalex.org/W2603340051","https://openalex.org/W2605118633","https://openalex.org/W2896133748","https://openalex.org/W2953092638","https://openalex.org/W2963069394","https://openalex.org/W2963951265","https://openalex.org/W2971775690","https://openalex.org/W3148931049","https://openalex.org/W4235741411"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"methods":[2],"for":[3],"calculating":[4],"a":[5,14,20,24,38,43,84,89,101],"measure":[6,54,70],"of":[7,26,45,62,91,106,117],"phonotactic":[8],"complexity\u2014bits":[9],"per":[10,56,111],"phoneme\u2014":[11],"that":[12,63],"permits":[13],"straightforward":[15],"cross-linguistic":[16],"comparison.":[17],"When":[18],"given":[19],"word,":[21],"represented":[22],"as":[23,30],"sequence":[25],"phonemic":[27],"segments":[28],"such":[29],"symbols":[31],"in":[32],"the":[33,49,59,66,75,114],"international":[34],"phonetic":[35],"alphabet,":[36],"and":[37,113],"statistical":[39],"model":[40],"trained":[41],"on":[42],"sample":[44],"word":[46,64],"types":[47],"from":[48],"language,":[50],"we":[51,99],"can":[52],"approximately":[53],"bits":[55,110],"phoneme":[57,112],"using":[58],"negative":[60,104],"log-probability":[61],"under":[65],"model.":[67],"This":[68],"simple":[69],"allows":[71],"us":[72],"to":[73],"compare":[74],"entropy":[76],"across":[77,96],"languages,":[78,98],"giving":[79],"insight":[80],"into":[81],"how":[82],"complex":[83],"language\u2019s":[85],"phonotactics":[86],"is.":[87],"Using":[88],"collection":[90],"1016":[92],"basic":[93],"concept":[94],"words":[95],"106":[97],"demonstrate":[100],"very":[102],"strong":[103],"correlation":[105],"\u2212":[107],"0.74":[108],"between":[109],"average":[115],"length":[116],"words.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2020-01-30T00:00:00"}