{"id":"https://openalex.org/W2741281060","doi":"https://doi.org/10.24963/ijcai.2017/376","title":"Compressed Nonparametric Language Modelling","display_name":"Compressed Nonparametric Language Modelling","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2741281060","doi":"https://doi.org/10.24963/ijcai.2017/376","mag":"2741281060"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/376","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/376","pdf_url":"https://www.ijcai.org/proceedings/2017/0376.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0376.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086032589","display_name":"Ehsan Shareghi","orcid":null},"institutions":[{"id":"https://openalex.org/I2801239119","display_name":"Australian Regenerative Medicine Institute","ror":"https://ror.org/02qa5kg76","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2801037857","https://openalex.org/I2801239119","https://openalex.org/I56590836"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ehsan Shareghi","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I2801239119","https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081525024","display_name":"Gholamreza Haffari","orcid":"https://orcid.org/0000-0001-7326-8380"},"institutions":[{"id":"https://openalex.org/I2801239119","display_name":"Australian Regenerative Medicine Institute","ror":"https://ror.org/02qa5kg76","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2801037857","https://openalex.org/I2801239119","https://openalex.org/I56590836"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gholamreza Haffari","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I2801239119","https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078530959","display_name":"Trevor Cohn","orcid":"https://orcid.org/0000-0003-4363-1673"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Trevor Cohn","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8261,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80642396,"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":"2701","last_page":"2707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8748455047607422},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.8216241598129272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7734082937240601},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7275482416152954},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5460179448127747},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5443997979164124},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4498434066772461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44160905480384827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4387022852897644},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3731279969215393},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.10621842741966248}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8748455047607422},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.8216241598129272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734082937240601},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7275482416152954},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5460179448127747},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5443997979164124},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4498434066772461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44160905480384827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4387022852897644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3731279969215393},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.10621842741966248},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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":2,"locations":[{"id":"doi:10.24963/ijcai.2017/376","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/376","pdf_url":"https://www.ijcai.org/proceedings/2017/0376.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:monash.edu:publications/e4cdf9bd-c50d-4a43-95db-82e91914c34c","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/e4cdf9bd-c50d-4a43-95db-82e91914c34c","pdf_url":null,"source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Shareghi , E , Haffari , G & Cohn , T 2017 , Compressed nonparametric language modelling . in C Sierra (ed.) , 26th International Joint Conference on Artificial Intelligence, IJCAI 2017 . Association for the Advancement of Artificial Intelligence (AAAI) , Marina del Rey CA USA , pp. 2701-2707 , International Joint Conference on Artificial Intelligence 2017 , Melbourne , Victoria , Australia , 19/08/17 . https://doi.org/10.24963/ijcai.2017/376","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/376","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/376","pdf_url":"https://www.ijcai.org/proceedings/2017/0376.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310369","display_name":"National ICT Australia","ror":"https://ror.org/03q397159"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741281060.pdf","grobid_xml":"https://content.openalex.org/works/W2741281060.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1549037892","https://openalex.org/W1631260214","https://openalex.org/W1934041838","https://openalex.org/W2005902041","https://openalex.org/W2038339694","https://openalex.org/W2041445031","https://openalex.org/W2044905690","https://openalex.org/W2087309226","https://openalex.org/W2113430702","https://openalex.org/W2115529864","https://openalex.org/W2131924950","https://openalex.org/W2154099718","https://openalex.org/W2158195707","https://openalex.org/W2158266063","https://openalex.org/W2158874082","https://openalex.org/W2161488606","https://openalex.org/W2250653840","https://openalex.org/W2250988012","https://openalex.org/W2533248932","https://openalex.org/W2567188764","https://openalex.org/W2952380754","https://openalex.org/W2963766645"],"related_works":["https://openalex.org/W2140979028","https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W4287323699","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467"],"abstract_inverted_index":{"Hierarchical":[0],"Pitman-Yor":[1],"Process":[2],"priors":[3],"are":[4],"compelling":[5],"for":[6,113],"learning":[7],"language":[8],"models,":[9,104],"outperforming":[10,118],"point-estimate":[11],"based":[12],"methods.":[13],"However,":[14],"these":[15],"models":[16],"remain":[17],"unpopular":[18],"due":[19],"to":[20,76,101,131],"computational":[21],"and":[22,29,79,115,117],"statistical":[23],"inference":[24,63,84],"issues,":[25],"such":[26],"as":[27,32,34],"memory":[28,73],"time":[30],"usage,":[31],"well":[33],"poor":[35],"mixing":[36],"of":[37,109,121],"sampler.":[38],"In":[39],"this":[40,66],"work":[41],"we":[42,58],"propose":[43],"a":[44,70],"novel":[45],"framework":[46,67],"which":[47],"represents":[48],"the":[49,83,119,122],"HPYP":[50,78,103],"model":[51,92],"compactly":[52],"using":[53],"compressed":[54],"suffix":[55],"trees.":[56],"Then,":[57],"develop":[59],"an":[60],"efficient":[61],"approximate":[62],"scheme":[64],"in":[65,82],"that":[68,90],"has":[69],"much":[71],"lower":[72],"footprint":[74],"compared":[75,100],"full":[77],"is":[80],"fast":[81,112],"time.":[85],"The":[86],"experimental":[87],"results":[88],"illustrate":[89],"our":[91],"can":[93],"be":[94],"built":[95],"on":[96],"significantly":[97],"larger":[98],"datasets":[99],"previous":[102],"while":[105],"being":[106],"several":[107],"orders":[108],"magnitudes":[110],"smaller,":[111],"training":[114],"inference,":[116],"perplexity":[120],"state-of-the-art":[123],"Modified":[124],"Kneser-Ney":[125],"count-based":[126],"LM":[127],"smoothing":[128],"by":[129],"up":[130],"15%.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}