{"id":"https://openalex.org/W2150299430","doi":"https://doi.org/10.3115/v1/p14-2112","title":"Exponential Reservoir Sampling for Streaming Language Models","display_name":"Exponential Reservoir Sampling for Streaming Language Models","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2150299430","doi":"https://doi.org/10.3115/v1/p14-2112","mag":"2150299430"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-2112","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2112","pdf_url":"https://aclanthology.org/P14-2112.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/P14-2112.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058230090","display_name":"Miles Osborne","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I20577493","display_name":"Denison University","ror":"https://ror.org/05pqx1c24","country_code":"US","type":"education","lineage":["https://openalex.org/I20577493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miles Osborne","raw_affiliation_strings":["School of Informatics University of Edinburgh","Johns Hopkins University","Mathematics and Computer Science Denison University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh","institution_ids":[]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Mathematics and Computer Science Denison University","institution_ids":["https://openalex.org/I20577493"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085185917","display_name":"Ashwin Lall","orcid":"https://orcid.org/0009-0003-2046-0055"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I20577493","display_name":"Denison University","ror":"https://ror.org/05pqx1c24","country_code":"US","type":"education","lineage":["https://openalex.org/I20577493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin Lall","raw_affiliation_strings":["School of Informatics University of Edinburgh","Mathematics and Computer Science Denison University","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh","institution_ids":[]},{"raw_affiliation_string":"Mathematics and Computer Science Denison University","institution_ids":["https://openalex.org/I20577493"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075825791","display_name":"Benjamin Van Durme","orcid":"https://orcid.org/0000-0003-4328-4288"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I20577493","display_name":"Denison University","ror":"https://ror.org/05pqx1c24","country_code":"US","type":"education","lineage":["https://openalex.org/I20577493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Van Durme","raw_affiliation_strings":["Mathematics and Computer Science Denison University","Johns Hopkins University","School of Informatics University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Denison University","institution_ids":["https://openalex.org/I20577493"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"School of Informatics University of Edinburgh","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8062,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94028045,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"687","last_page":"692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9943000078201294,"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":0.889735221862793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7656667232513428},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.7389798760414124},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5714765787124634},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.542630136013031},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.5200899839401245},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.43460729718208313},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3275521397590637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29942500591278076},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22577053308486938},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.1113336980342865},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11104050278663635},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.08395817875862122}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.889735221862793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656667232513428},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7389798760414124},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5714765787124634},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.542630136013031},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.5200899839401245},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.43460729718208313},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3275521397590637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29942500591278076},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22577053308486938},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.1113336980342865},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11104050278663635},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.08395817875862122},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/p14-2112","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2112","pdf_url":"https://aclanthology.org/P14-2112.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.9523","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.9523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://personal.denison.edu/~lalla/papers/acl2014.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.653.5644","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.653.5644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/P/P14/P14-2112.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-2112","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2112","pdf_url":"https://aclanthology.org/P14-2112.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150299430.pdf","grobid_xml":"https://content.openalex.org/works/W2150299430.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1562125942","https://openalex.org/W1975690018","https://openalex.org/W2044062612","https://openalex.org/W2053154469","https://openalex.org/W2065512234","https://openalex.org/W2102439588","https://openalex.org/W2106540279","https://openalex.org/W2119885577","https://openalex.org/W2120804083","https://openalex.org/W2134800885","https://openalex.org/W2146867136","https://openalex.org/W2163546841","https://openalex.org/W2171458318","https://openalex.org/W2250615155"],"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/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2902731467"],"abstract_inverted_index":{"We":[0],"show":[1],"how":[2],"rapidly":[3],"changing":[4],"textual":[5],"streams":[6],"such":[7],"as":[8,41],"Twitter":[9,38],"can":[10,70],"be":[11],"modelled":[12],"in":[13,61],"fixed":[14],"space.":[15],"Our":[16],"approach":[17],"is":[18],"based":[19,47],"upon":[20],"a":[21,42],"randomised":[22],"algorithm":[23],"called":[24],"Exponential":[25],"Reservoir":[26],"Sampling,":[27],"unexplored":[28],"by":[29],"this":[30],"community":[31],"until":[32],"now.":[33],"Using":[34],"language":[35],"models":[36],"over":[37],"and":[39],"Newswire":[40],"testbed,":[43],"our":[44],"experimental":[45],"results":[46],"on":[48],"perplexity":[49],"support":[50],"the":[51,62,68,78],"intuition":[52],"that":[53,59,65],"recently":[54],"observed":[55],"data":[56],"generally":[57],"outweighs":[58],"seen":[60],"past,":[63],"but":[64],"at":[66],"times,":[67],"past":[69],"have":[71],"valuable":[72],"signals":[73],"enabling":[74],"better":[75],"modelling":[76],"of":[77],"present.":[79]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}