{"id":"https://openalex.org/W2135533303","doi":"https://doi.org/10.1145/1390334.1390491","title":"Using parsimonious language models on web data","display_name":"Using parsimonious language models on web data","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W2135533303","doi":"https://doi.org/10.1145/1390334.1390491","mag":"2135533303"},"language":"en","primary_location":{"id":"doi:10.1145/1390334.1390491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual 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/A5089111917","display_name":"Rianne Kaptein","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rianne Kaptein","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands","university of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]},{"raw_affiliation_string":"university of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051795200","display_name":"Rongmei Li","orcid":"https://orcid.org/0000-0001-7324-1284"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rongmei LI","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108167267","display_name":"Djoerd Hiemstra","orcid":"https://orcid.org/0000-0003-4967-2900"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Djoerd Hiemstra","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044511901","display_name":"Jaap Kamps","orcid":"https://orcid.org/0000-0002-6614-0087"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jaap Kamps","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands","university of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]},{"raw_affiliation_string":"university of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10894165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"763","last_page":"764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9984999895095825,"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":0.861438512802124},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7602731585502625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5745714902877808},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5272195339202881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4911205470561981},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.4904451072216034},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4301499128341675},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42787477374076843},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12572592496871948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.861438512802124},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7602731585502625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5745714902877808},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5272195339202881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4911205470561981},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.4904451072216034},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4301499128341675},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42787477374076843},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12572592496871948},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1390334.1390491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/140ce2d7-5641-43a3-afac-e61ea2578c89","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/using-parsimonious-language-models-on-web-data(140ce2d7-5641-43a3-afac-e61ea2578c89).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kaptein, R, Li, R, Hiemstra, D & Kamps, J 2008, Using parsimonious language models on web data. in S H Myaeng, D W Oard, F Sebastiani, T S Chua & M K Leong (eds), ACM SIGIR 2008: 31st annual International ACM SIGIR Conference on Research and Development in Information Retrieval, July 20-24, 2008, Singapore: Proceedings. Association for Computing Machinery (ACM), New York, NY, pp. 763-764, 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2008), Singapore, 20/07/08. < http://doi.acm.org/10.1145/1390334.1390491 >","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/e43e33f2-029b-4691-aff8-325fcc1a69ad","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/e43e33f2-029b-4691-aff8-325fcc1a69ad","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kaptein, R, Li, R, Hiemstra, D & Kamps, J 2008, Using Parsimonious Language Models on Web Data. in T-S Chua & M-K Leong (eds), SIGIR '08 : Proceedings of the 31th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York NY, USA, pp. 763-764, 31st Annual International ACM/SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008, Singapore, Singapore, 20/07/08. https://doi.org/10.1145/1390334.1390491","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/227820","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/227820","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Myaeng, S.-H. (ed.), ACM SIGIR 2008: 31st annual international ACM SIGIR conference on Research and development in information retrieval, 20-24 July, Singapore. Proceedings, pp. 763-764","raw_type":"Article in monograph or in proceedings"},{"id":"pmh:oai:ris.utwente.nl:publications/e43e33f2-029b-4691-aff8-325fcc1a69ad","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W173200862","https://openalex.org/W342688938","https://openalex.org/W1486980688","https://openalex.org/W2169583766","https://openalex.org/W2792952625","https://openalex.org/W6611639712"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W2100945520","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W644339423","https://openalex.org/W2386525189","https://openalex.org/W2360284199"],"abstract_inverted_index":{"In":[0,67],"this":[1],"paper":[2],"we":[3],"explore":[4],"the":[5,22,47,58,70],"use":[6],"of":[7,54],"parsimonious":[8,48],"language":[9,24,49,60],"models":[10,15,25],"for":[11,31,62],"web":[12,33],"retrieval.":[13,34],"These":[14],"are":[16,27],"smaller":[17],"thus":[18],"more":[19,75],"efficient":[20],"than":[21,77],"standard":[23,59],"and":[26,44,65,74],"therefore":[28],"well":[29],"suited":[30],"large-scale":[32],"We":[35],"have":[36],"conducted":[37],"experiments":[38,80],"on":[39,81],"four":[40],"TREC":[41],"topic":[42],"sets,":[43],"found":[45],"that":[46],"model":[50,61],"results":[51],"in":[52,78],"improvement":[53,71],"retrieval":[55],"effectiveness":[56],"over":[57],"all":[63,68],"data-sets":[64],"measures.":[66],"cases":[69],"is":[72],"significant,":[73],"substantial":[76],"earlier":[79],"newspaper/newswire":[82],"data.":[83]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}