{"id":"https://openalex.org/W2160160425","doi":"https://doi.org/10.1145/1835449.1835619","title":"Hierarchical pitman-yor language model for information retrieval","display_name":"Hierarchical pitman-yor language model for information retrieval","publication_year":2010,"publication_date":"2010-07-19","ids":{"openalex":"https://openalex.org/W2160160425","doi":"https://doi.org/10.1145/1835449.1835619","mag":"2160160425"},"language":"en","primary_location":{"id":"doi:10.1145/1835449.1835619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","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/A5015201403","display_name":"Saeedeh Momtazi","orcid":"https://orcid.org/0000-0002-8110-1342"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Saeedeh Momtazi","raw_affiliation_strings":["Saarland University, Saarbrucken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saarland University, Saarbrucken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008875255","display_name":"Dietrich Klakow","orcid":"https://orcid.org/0000-0002-4147-9690"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dietrich Klakow","raw_affiliation_strings":["Saarland University, Saarbrucken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saarland University, Saarbrucken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.6976495385169983},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.6046836972236633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5871538519859314},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5248922109603882},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5126606822013855},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.5113632082939148},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.500035285949707},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4224734604358673},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41835343837738037},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.41790562868118286},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.41481897234916687},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.17402058839797974},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17298099398612976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6976495385169983},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.6046836972236633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871538519859314},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5248922109603882},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5126606822013855},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.5113632082939148},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.500035285949707},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4224734604358673},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41835343837738037},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.41790562868118286},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.41481897234916687},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.17402058839797974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17298099398612976},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1835449.1835619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.176.7438","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.176.7438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lsv.uni-saarland.de/personalPages/smomtazi/papers/SaeedehMomtazi-SIGIR10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2007553631","https://openalex.org/W2093390569","https://openalex.org/W2113939335","https://openalex.org/W2136542423","https://openalex.org/W2154099718","https://openalex.org/W4206765718","https://openalex.org/W4240913316"],"related_works":["https://openalex.org/W3121467232","https://openalex.org/W2393894849","https://openalex.org/W2107192713","https://openalex.org/W2027714503","https://openalex.org/W2544994990","https://openalex.org/W4254467987","https://openalex.org/W3190171609","https://openalex.org/W1531847006","https://openalex.org/W2170902875","https://openalex.org/W2005265490"],"abstract_inverted_index":{"In":[0],"this":[1,54],"paper,":[2],"we":[3],"propose":[4],"a":[5,22,32],"new":[6],"application":[7],"of":[8,24,38,42],"Bayesian":[9],"language":[10],"model":[11,20,55],"based":[12],"on":[13,50],"Pitman-Yor":[14,29],"process":[15,30],"for":[16],"information":[17],"retrieval.":[18],"This":[19],"is":[21,36],"generalization":[23],"the":[25,39,57,63],"Dirichlet":[26,66],"distribution.":[27],"The":[28],"creates":[31],"power-law":[33],"distribution":[34],"which":[35],"one":[37],"statistical":[40],"properties":[41],"word":[43],"frequency":[44],"in":[45],"natural":[46],"language.":[47],"Our":[48],"experiments":[49],"Robust04":[51],"indicate":[52],"that":[53],"improves":[56],"document":[58],"retrieval":[59],"performance":[60],"compared":[61],"to":[62],"commonly":[64],"used":[65],"prior":[67],"and":[68],"absolute":[69],"discounting":[70],"smoothing":[71],"techniques.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}