{"id":"https://openalex.org/W2163922101","doi":"https://doi.org/10.1145/1571941.1572061","title":"Compression-based document length prior for language models","display_name":"Compression-based document length prior for language models","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2163922101","doi":"https://doi.org/10.1145/1571941.1572061","mag":"2163922101"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1572061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","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/A5046723532","display_name":"Javier Parapar","orcid":"https://orcid.org/0000-0002-5997-8252"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Parapar","raw_affiliation_strings":["University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020247368","display_name":"David E. Losada","orcid":"https://orcid.org/0000-0001-8823-7501"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David E. Losada","raw_affiliation_strings":["University of Santiago de Compostela, Santiago de Compostela, Spain"],"affiliations":[{"raw_affiliation_string":"University of Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056469959","display_name":"\u00c1lvaro Barreiro","orcid":"https://orcid.org/0000-0002-6698-2946"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1lvaro Barreiro","raw_affiliation_strings":["University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046723532"],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":null,"apc_paid":null,"fwci":0.4516,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75795582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"652","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8048516511917114},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7641814947128296},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.7553955316543579},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.6637147068977356},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5868902802467346},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.473691463470459},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4375627338886261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4319581091403961},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4304758310317993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3798244297504425},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3544420301914215},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0877256989479065},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07528769969940186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8048516511917114},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7641814947128296},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7553955316543579},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.6637147068977356},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5868902802467346},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.473691463470459},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4375627338886261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4319581091403961},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4304758310317993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3798244297504425},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3544420301914215},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0877256989479065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07528769969940186},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1571941.1572061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.3033","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.3033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dc.fi.udc.es/~barreiro/publications/parapar_et_al_sigir2009.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.3624","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.3624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-gsi.dec.usc.es/ir/pdf/sigir09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1953638699","https://openalex.org/W1972594981","https://openalex.org/W2000569744","https://openalex.org/W2084929085","https://openalex.org/W2128859735","https://openalex.org/W4234200495","https://openalex.org/W6628905179"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013"],"abstract_inverted_index":{"The":[0,66],"inclusion":[1],"of":[2,14,30,48,60],"document":[3,41],"length":[4,42],"factors":[5],"has":[6],"been":[7],"a":[8,39],"major":[9],"topic":[10],"in":[11,57,75],"the":[12,31,46,49,58],"development":[13],"retrieval":[15],"models.":[16],"We":[17],"believe":[18],"that":[19,44],"current":[20],"models":[21],"can":[22],"be":[23],"further":[24],"improved":[25],"by":[26],"more":[27],"refined":[28],"estimations":[29],"document's":[32],"scope.":[33],"In":[34],"this":[35],"poster":[36],"we":[37],"present":[38],"new":[40,53],"prior":[43,54],"uses":[45],"size":[47],"compressed":[50],"document.":[51],"This":[52],"is":[55],"introduced":[56],"context":[59],"Language":[61],"Modeling":[62],"with":[63],"Dirichlet":[64],"smoothing.":[65],"evaluation":[67],"performed":[68],"on":[69],"several":[70],"collections":[71],"shows":[72],"significant":[73],"improvements":[74],"effectiveness.":[76]},"counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
