{"id":"https://openalex.org/W2113939335","doi":"https://doi.org/10.1109/icassp.2010.5495007","title":"Power law discounting for n-gram language models","display_name":"Power law discounting for n-gram language models","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2113939335","doi":"https://doi.org/10.1109/icassp.2010.5495007","mag":"2113939335"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047856952","display_name":"Songfang Huang","orcid":"https://orcid.org/0000-0001-8084-0904"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Songfang Huang","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":null,"first_page":"5178","last_page":"5181"},"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":0.9991000294685364,"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":0.9977999925613403,"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/perplexity","display_name":"Perplexity","score":0.7656103372573853},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7101732492446899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5970399379730225},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5766229629516602},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.5582225918769836},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5065516233444214},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.486258864402771},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.45148733258247375},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.39229410886764526},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34559404850006104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33299338817596436},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2548040449619293},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24095419049263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22492027282714844},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08723562955856323}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7656103372573853},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7101732492446899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5970399379730225},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5766229629516602},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.5582225918769836},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5065516233444214},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.486258864402771},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.45148733258247375},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.39229410886764526},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34559404850006104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33299338817596436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2548040449619293},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24095419049263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22492027282714844},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08723562955856323},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2010.5495007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.5183","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.5183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2010/huang-icassp10.pdf","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/4553","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/4553","pdf_url":null,"source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1631260214","https://openalex.org/W1934041838","https://openalex.org/W2005902041","https://openalex.org/W2007553631","https://openalex.org/W2027499299","https://openalex.org/W2087309226","https://openalex.org/W2101051131","https://openalex.org/W2122560783","https://openalex.org/W2132957691","https://openalex.org/W2154099718","https://openalex.org/W2156833271","https://openalex.org/W2158195707","https://openalex.org/W2159399018","https://openalex.org/W2484412399","https://openalex.org/W6636811518","https://openalex.org/W6651757226","https://openalex.org/W6652304018","https://openalex.org/W6679162469","https://openalex.org/W6682871038","https://openalex.org/W6683650587"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"We":[0,49],"present":[1],"an":[2],"approximation":[3],"to":[4,43,79,102,113],"the":[5,14,56,62,114],"Bayesian":[6],"hierarchical":[7,115],"Pitman-Yor":[8,116],"process":[9,117],"language":[10,73,118],"model":[11,74],"which":[12,32],"maintains":[13],"power":[15,35,87],"law":[16,36,88],"distribution":[17],"over":[18],"word":[19,98],"tokens,":[20],"while":[21,109],"not":[22],"requiring":[23],"a":[24,39,66,72],"computationally":[25],"expensive":[26],"approximate":[27],"inference":[28],"process.":[29],"This":[30],"approximation,":[31],"we":[33],"term":[34],"discounting,":[37],"has":[38],"similar":[40,111],"computational":[41],"complexity":[42],"interpolated":[44,104],"and":[45,61,71,97,105],"modified":[46,106],"Kneser-Ney":[47,107],"smoothing.":[48],"performed":[50],"experiments":[51],"on":[52],"meeting":[53],"transcription":[54],"using":[55],"NIST":[57],"RT06s":[58],"evaluation":[59],"data":[60],"AMI":[63],"corpus,":[64],"with":[65],"vocabulary":[67],"of":[68,77],"50,000":[69],"words":[70],"training":[75],"set":[76],"up":[78],"211":[80],"million":[81],"words.":[82],"Our":[83],"results":[84,90,112],"indicate":[85],"that":[86],"discounting":[89],"in":[91,95],"statistically":[92],"significant":[93],"reductions":[94],"perplexity":[96],"error":[99],"rate":[100],"compared":[101],"both":[103],"smoothing,":[108],"producing":[110],"model.":[119]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}