{"id":"https://openalex.org/W2564413773","doi":"https://doi.org/10.18653/v1/w16-6637","title":"An Analysis of the Ability of Statistical Language Models to Capture the Structural Properties of Language","display_name":"An Analysis of the Ability of Statistical Language Models to Capture the Structural Properties of Language","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2564413773","doi":"https://doi.org/10.18653/v1/w16-6637","mag":"2564413773"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-6637","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-6637","pdf_url":"https://www.aclweb.org/anthology/W16-6637.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 9th International Natural Language Generation conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-6637.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083561499","display_name":"Aneiss Ghodsi","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aneiss Ghodsi","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072072153","display_name":"John DeNero","orcid":"https://orcid.org/0000-0001-9152-3891"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John DeNero","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083561499"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.8569,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84789099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9968000054359436,"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/T10320","display_name":"Neural Networks and Applications","score":0.993399977684021,"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":0.819212019443512},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7872382998466492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6307355165481567},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5657755732536316},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.494759738445282},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.47453486919403076},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.45091044902801514},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.2811715602874756},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.210818350315094},{"id":"https://openalex.org/keywords/comprehension-approach","display_name":"Comprehension approach","score":0.15563997626304626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819212019443512},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7872382998466492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6307355165481567},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5657755732536316},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.494759738445282},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.47453486919403076},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.45091044902801514},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.2811715602874756},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.210818350315094},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.15563997626304626},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-6637","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-6637","pdf_url":"https://www.aclweb.org/anthology/W16-6637.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 9th International Natural Language Generation conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-6637","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-6637","pdf_url":"https://www.aclweb.org/anthology/W16-6637.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 9th International Natural Language Generation conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2564413773.pdf","grobid_xml":"https://content.openalex.org/works/W2564413773.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1631260214","https://openalex.org/W1632114991","https://openalex.org/W2064675550","https://openalex.org/W2158195707","https://openalex.org/W2171928131"],"related_works":["https://openalex.org/W4255155614","https://openalex.org/W2394860946","https://openalex.org/W761725120","https://openalex.org/W2009170886","https://openalex.org/W2071315630","https://openalex.org/W2897427480","https://openalex.org/W1508853749","https://openalex.org/W1745277","https://openalex.org/W2310188530","https://openalex.org/W1463944445"],"abstract_inverted_index":{"We":[0,59,95],"investigate":[1],"the":[2,16,46,73,84,87,92],"characteristics":[3,120],"and":[4,10,48,55,82,107,124],"quantifiable":[5],"predispositions":[6],"of":[7,18,42,45,86,102,118,121,143],"both":[8],"n-gram":[9,105],"recurrent":[11,109],"neural":[12,24,110],"language":[13,19,54,111,144],"models":[14,25,47,106],"in":[15,137],"framework":[17,136],"generation.":[20],"In":[21],"modern":[22],"applications,":[23],"have":[26,32],"been":[27],"widely":[28],"adopted,":[29],"as":[30],"they":[31,50],"empirically":[33],"provided":[34],"better":[35],"results.":[36],"However,":[37],"there":[38],"is":[39],"a":[40,116,135],"lack":[41],"deep":[43],"analysis":[44,89,142],"how":[49],"relate":[51],"to":[52,61,79,83,91,139],"real":[53],"its":[56],"structural":[57],"properties.":[58],"attempt":[60],"perform":[62,140],"such":[63],"an":[64],"investigation":[65],"by":[66,70],"analyzing":[67],"corpora":[68],"generated":[69],"sampling":[71],"from":[72],"models.":[74,112,145],"The":[75],"results":[76,85,114],"are":[77],"compared":[78],"each":[80,122],"other":[81],"same":[88],"applied":[90],"training":[93],"corpus.":[94],"carried":[96],"out":[97],"these":[98],"experiments":[99],"on":[100],"varieties":[101],"Kneser-Ney":[103],"smoothed":[104],"basic":[108],"Our":[113,130],"reveal":[115],"number":[117],"distinctive":[119],"model,":[123],"offer":[125],"insights":[126],"into":[127],"their":[128],"behavior.":[129],"general":[131],"approach":[132],"also":[133],"provides":[134],"which":[138],"further":[141]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}