{"id":"https://openalex.org/W2090043440","doi":"https://doi.org/10.1145/1772690.1772836","title":"Optimizing two stage bigram language models for IR","display_name":"Optimizing two stage bigram language models for IR","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W2090043440","doi":"https://doi.org/10.1145/1772690.1772836","mag":"2090043440"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","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/A5078278687","display_name":"Sara Javanmardi","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sara Javanmardi","raw_affiliation_strings":["University of California Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041659067","display_name":"Kuansan Wang","orcid":"https://orcid.org/0000-0001-7089-7966"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuansan Wang","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078278687"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":2.7929,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91245962,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1125","last_page":"1126"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9983999729156494,"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/bigram","display_name":"Bigram","score":0.9948753118515015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7908369302749634},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.7648380994796753},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6622036695480347},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6365056037902832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384820103645325},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5218366980552673},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4848393201828003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3817690908908844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33812665939331055},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.15375971794128418},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12245258688926697}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9948753118515015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908369302749634},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7648380994796753},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6622036695480347},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6365056037902832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384820103645325},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5218366980552673},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4848393201828003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3817690908908844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33812665939331055},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.15375971794128418},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12245258688926697},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1772690.1772836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.9149","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.9149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/%7Esjavanma/MSR-Report.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1972594981","https://openalex.org/W2030760474","https://openalex.org/W2069870183","https://openalex.org/W2070740689","https://openalex.org/W2114013702","https://openalex.org/W2136542423","https://openalex.org/W2155229791","https://openalex.org/W2160825952","https://openalex.org/W2162746367"],"related_works":["https://openalex.org/W2105076537","https://openalex.org/W1700330385","https://openalex.org/W2197825247","https://openalex.org/W2002221802","https://openalex.org/W2041167939","https://openalex.org/W2250909759","https://openalex.org/W2562995433","https://openalex.org/W2131111393","https://openalex.org/W2028371633","https://openalex.org/W2020757772"],"abstract_inverted_index":{"Although":[0],"higher":[1,37],"order":[2,38],"language":[3],"models":[4,69],"(LMs)":[5],"have":[6],"shown":[7],"benefit":[8],"of":[9,18,22],"capturing":[10],"word":[11],"dependencies":[12],"for":[13],"Information":[14],"retrieval(IR),":[15],"the":[16,19,45,52,102],"tuning":[17,54],"increased":[20],"number":[21],"free":[23],"parameters":[24],"remains":[25],"a":[26,57,61,92],"formidable":[27],"engineering":[28],"challenge.":[29],"Consequently,in":[30],"many":[31],"real":[32],"world":[33],"retrieval":[34],"systems,":[35],"applying":[36],"LMs":[39,78],"is":[40],"an":[41],"exception":[42],"rather":[43],"than":[44],"rule.":[46],"In":[47],"this":[48],"study,":[49],"we":[50,85],"address":[51],"parameter":[53],"problem":[55],"using":[56],"framework":[58],"based":[59],"on":[60],"linear":[62],"ranking":[63],"model":[64],"in":[65],"which":[66],"different":[67],"component":[68],"are":[70],"incorporated":[71],"as":[72,83],"features.":[73],"Using":[74],"unigram":[75,99],"and":[76,101],"bigram":[77,93],"with":[79],"2":[80],"stage":[81],"smoothing":[82],"examples,":[84],"show":[86],"that":[87,95],"our":[88],"method":[89],"leads":[90],"to":[91],"LM":[94],"outperforms":[96],"significantly":[97],"its":[98],"counterpart":[100],"well-tuned":[103],"BM25":[104],"model.":[105]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}