{"id":"https://openalex.org/W2144630266","doi":"https://doi.org/10.3115/v1/d14-1182","title":"Sometimes Average is Best: The Importance of Averaging for Prediction using MCMC Inference in Topic Modeling","display_name":"Sometimes Average is Best: The Importance of Averaging for Prediction using MCMC Inference in Topic Modeling","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2144630266","doi":"https://doi.org/10.3115/v1/d14-1182","mag":"2144630266"},"language":"en","primary_location":{"id":"doi:10.3115/v1/d14-1182","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1182","pdf_url":"https://aclanthology.org/D14-1182.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 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D14-1182.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080426723","display_name":"Viet-An Nguyen","orcid":"https://orcid.org/0000-0002-7923-0882"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Viet-An Nguyen","raw_affiliation_strings":["Computer Science University of Maryland College Park, MD","University of Maryland, College Park, College Park, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science University of Maryland College Park, MD","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, College Park, United States","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081307846","display_name":"Jordan Boyd\u2010Graber","orcid":"https://orcid.org/0000-0002-7770-4431"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]},{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jordan Boyd-Graber","raw_affiliation_strings":["Computer Science University of Colorado Boulder, CO","University of Maryland, College Park, College Park, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science University of Colorado Boulder, CO","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"University of Maryland, College Park, College Park, United States","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059946729","display_name":"Philip Resnik","orcid":"https://orcid.org/0000-0002-6130-8602"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Resnik","raw_affiliation_strings":["Linguistics and UMIACS University of Maryland College Park, MD","University of Maryland, College Park, College Park, United States"],"affiliations":[{"raw_affiliation_string":"Linguistics and UMIACS University of Maryland College Park, MD","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, College Park, United States","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080426723"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":2.9599,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92454074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1752","last_page":"1757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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":0.9986000061035156,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9945999979972839,"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/inference","display_name":"Inference","score":0.7408763766288757},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.66706782579422},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.604915976524353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47388380765914917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47275644540786743},{"id":"https://openalex.org/keywords/predictive-inference","display_name":"Predictive inference","score":0.449365496635437},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.41690120100975037},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.39128032326698303},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.32065197825431824},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3134661912918091},{"id":"https://openalex.org/keywords/frequentist-inference","display_name":"Frequentist inference","score":0.3020337224006653},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.23635199666023254},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20983171463012695}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7408763766288757},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.66706782579422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.604915976524353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47388380765914917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47275644540786743},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.449365496635437},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.41690120100975037},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.39128032326698303},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32065197825431824},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3134661912918091},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.3020337224006653},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.23635199666023254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20983171463012695}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/d14-1182","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1182","pdf_url":"https://aclanthology.org/D14-1182.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 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/d14-1182","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1182","pdf_url":"https://aclanthology.org/D14-1182.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 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8840828949","display_name":"SoCS: Collaborative Research: Data Driven, Computational Models for Discovery and Analysis of Framing","funder_award_id":"1211153","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2144630266.pdf","grobid_xml":"https://content.openalex.org/works/W2144630266.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W195465510","https://openalex.org/W1508001288","https://openalex.org/W1576520375","https://openalex.org/W1880262756","https://openalex.org/W1969486090","https://openalex.org/W2044429219","https://openalex.org/W2051434435","https://openalex.org/W2096476966","https://openalex.org/W2098062695","https://openalex.org/W2100931213","https://openalex.org/W2101101940","https://openalex.org/W2103878673","https://openalex.org/W2116330964","https://openalex.org/W2117614723","https://openalex.org/W2122683976","https://openalex.org/W2135194391","https://openalex.org/W2140124448","https://openalex.org/W2144100511","https://openalex.org/W2144673827","https://openalex.org/W2152677317","https://openalex.org/W2156693754","https://openalex.org/W2160409620","https://openalex.org/W2161050705","https://openalex.org/W2161353674","https://openalex.org/W2163455955","https://openalex.org/W2172135926","https://openalex.org/W2174706414","https://openalex.org/W2334889010","https://openalex.org/W2952186591","https://openalex.org/W4231510805","https://openalex.org/W4252381709","https://openalex.org/W4399639051"],"related_works":["https://openalex.org/W88131178","https://openalex.org/W2478683457","https://openalex.org/W4235385816","https://openalex.org/W4251525937","https://openalex.org/W4242294605","https://openalex.org/W38714290","https://openalex.org/W3022940228","https://openalex.org/W4239322872","https://openalex.org/W2962956395","https://openalex.org/W2111053936"],"abstract_inverted_index":{"Markov":[0],"chain":[1],"Monte":[2],"Carlo":[3],"(MCMC)":[4],"approximates":[5],"the":[6],"posterior":[7],"distribution":[8],"of":[9],"latent":[10],"variable":[11],"models":[12],"by":[13],"generating":[14],"many":[15],"samples":[16,51],"and":[17,52],"averaging":[18,41,49,56],"over":[19],"them.":[20],"In":[21],"practice,":[22],"however,":[23],"it":[24],"is":[25],"often":[26],"more":[27],"convenient":[28],"to":[29,59],"cut":[30],"corners,":[31],"using":[32],"only":[33],"a":[34,39],"single":[35],"sample":[36],"or":[37],"following":[38],"suboptimal":[40],"strategy.":[42],"We":[43],"systematically":[44],"study":[45],"different":[46],"strategies":[47],"for":[48],"MCMC":[50],"show":[53],"empirically":[54],"that":[55],"properly":[57],"leads":[58],"significant":[60],"improvements":[61],"in":[62],"prediction.":[63]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}