{"id":"https://openalex.org/W2120826678","doi":"https://doi.org/10.1145/1553374.1553518","title":"A stochastic memoizer for sequence data","display_name":"A stochastic memoizer for sequence data","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2120826678","doi":"https://doi.org/10.1145/1553374.1553518","mag":"2120826678"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},"type":"article","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/A5017069785","display_name":"Frank Wood","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Frank Wood","raw_affiliation_strings":["University College London, London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021107714","display_name":"C\u00e9dric Archambeau","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C\u00e9dric Archambeau","raw_affiliation_strings":["University College London, London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048713693","display_name":"Jan Gasthaus","orcid":"https://orcid.org/0000-0002-2007-773X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jan Gasthaus","raw_affiliation_strings":["University College London, London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034793792","display_name":"Lancelot F. James","orcid":"https://orcid.org/0000-0002-7935-7584"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lancelot James","raw_affiliation_strings":["Hong Kong University of Science and Technology, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064373793","display_name":"Yee Whye Teh","orcid":"https://orcid.org/0000-0001-5365-6933"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yee Whye Teh","raw_affiliation_strings":["University College London, London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, London, UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017069785"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":14.0598,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.98958917,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1129","last_page":"1136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998999834060669,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998999834060669,"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":0.9983999729156494,"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/T12072","display_name":"Machine Learning and Algorithms","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/sequence","display_name":"Sequence (biology)","score":0.7543947696685791},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6428516507148743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6196200847625732},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5563532114028931},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.497297078371048},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.44251886010169983},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.4414425492286682},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4193049371242523},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.4115085005760193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3806501626968384},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33431583642959595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25714266300201416}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7543947696685791},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6428516507148743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6196200847625732},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5563532114028931},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.497297078371048},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.44251886010169983},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.4414425492286682},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4193049371242523},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4115085005760193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806501626968384},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33431583642959595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25714266300201416},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1553374.1553518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-16059","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-16059","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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"},{"id":"pmh:oai:repository.ust.hk:1783.1-16059","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-71149086686&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1486498012","https://openalex.org/W1890754682","https://openalex.org/W1965784613","https://openalex.org/W2059513841","https://openalex.org/W2065794571","https://openalex.org/W2072169887","https://openalex.org/W2087309226","https://openalex.org/W2089319476","https://openalex.org/W2103731025","https://openalex.org/W2131462252","https://openalex.org/W2135226297","https://openalex.org/W2154099718","https://openalex.org/W2154292407","https://openalex.org/W2158266063","https://openalex.org/W2533248932","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W6639796194","https://openalex.org/W6682718134"],"related_works":["https://openalex.org/W2407375987","https://openalex.org/W2505726097","https://openalex.org/W2950975704","https://openalex.org/W2010643158","https://openalex.org/W3049691116","https://openalex.org/W2106867672","https://openalex.org/W4310268968","https://openalex.org/W3081214562","https://openalex.org/W2753713401","https://openalex.org/W2053745677"],"abstract_inverted_index":{"We":[0,53,83,105],"propose":[1],"an":[2,48],"unbounded-depth,":[3],"hierarchical,":[4],"Bayesian":[5],"nonparametric":[6],"model":[7,13,41,64,92],"for":[8],"discrete":[9],"sequence":[10,108],"data.":[11],"This":[12],"can":[14,68],"be":[15,69],"estimated":[16],"from":[17],"a":[18,33,44,91,114],"single":[19],"training":[20,81],"sequence,":[21],"yet":[22],"shares":[23],"statistical":[24],"strength":[25],"between":[26],"subsequent":[27],"symbol":[28],"predictive":[29,36,103],"distributions":[30],"in":[31,71,76,89],"such":[32,90],"way":[34],"that":[35,67],"performance":[37],"generalizes":[38],"well.":[39],"The":[40],"builds":[42],"on":[43],"specific":[45],"parameterization":[46],"of":[47,79],"unbounded-depth":[49],"hierarchical":[50],"Pitman-Yor":[51],"process.":[52],"introduce":[54,97],"analytic":[55],"marginalization":[56],"steps":[57],"(using":[58],"coagulation":[59],"operators)":[60],"to":[61,65,86,101],"reduce":[62],"this":[63],"one":[66],"represented":[70],"time":[72],"and":[73,96],"space":[74],"linear":[75],"the":[77,80,107],"length":[78],"sequence.":[82],"show":[84],"how":[85],"perform":[87],"inference":[88],"without":[93],"truncation":[94],"approximation":[95],"fragmentation":[98],"operators":[99],"necessary":[100],"do":[102],"inference.":[104],"demonstrate":[106],"memoizer":[109],"by":[110],"using":[111],"it":[112],"as":[113],"language":[115],"model,":[116],"achieving":[117],"state-of-the-art":[118],"results.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":8}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}