{"id":"https://openalex.org/W1554694706","doi":"https://doi.org/10.5075/epfl-thesis-4088","title":"Machine learning for information retrieval","display_name":"Machine learning for information retrieval","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W1554694706","doi":"https://doi.org/10.5075/epfl-thesis-4088","mag":"1554694706"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.tind.io:118666","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/118666","pdf_url":"http://infoscience.epfl.ch/record/118666","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/118666","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Grangier, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5065912572"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9839000105857849,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9839000105857849,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.963699996471405,"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/T10320","display_name":"Neural Networks and Applications","score":0.9370999932289124,"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":0.8345404863357544},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7133793234825134},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6816398501396179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779327750205994},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.5625337362289429},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5558908581733704},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5204198956489563},{"id":"https://openalex.org/keywords/term-discrimination","display_name":"Term Discrimination","score":0.49650174379348755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4719589948654175},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4687970280647278},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4339182376861572},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3375508487224579},{"id":"https://openalex.org/keywords/concept-search","display_name":"Concept search","score":0.27948230504989624},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.2617049813270569},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.22023123502731323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345404863357544},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7133793234825134},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6816398501396179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779327750205994},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.5625337362289429},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5558908581733704},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5204198956489563},{"id":"https://openalex.org/C22639730","wikidata":"https://www.wikidata.org/wiki/Q7702546","display_name":"Term Discrimination","level":5,"score":0.49650174379348755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4719589948654175},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4687970280647278},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4339182376861572},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3375508487224579},{"id":"https://openalex.org/C182861755","wikidata":"https://www.wikidata.org/wiki/Q5158391","display_name":"Concept search","level":4,"score":0.27948230504989624},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.2617049813270569},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.22023123502731323},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"pmh:oai:infoscience.tind.io:118666","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/118666","pdf_url":"http://infoscience.epfl.ch/record/118666","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},{"id":"pmh:oai:infoscience.tind.io:146418","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146418","pdf_url":"http://infoscience.epfl.ch/record/146418","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/146418","raw_type":"Text"},{"id":"pmh:doi:10.5075/epfl-thesis-4088","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.175.1496","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.175.1496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/reports/2008/grangier-rr-08-34.pdf","raw_type":"text"},{"id":"pmh:oai:doc.rero.ch:11119","is_oa":false,"landing_page_url":"http://library.epfl.ch/theses/?nr=4088","pdf_url":null,"source":{"id":"https://openalex.org/S4306400148","display_name":"reroDoc Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:infoscience.epfl.ch:146042","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146042","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.5075/epfl-thesis-4088","is_oa":true,"landing_page_url":"https://doi.org/10.5075/epfl-thesis-4088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"mag:1554694706","is_oa":false,"landing_page_url":"http://publications.idiap.ch/downloads/papers/2008/Grangier_THESIS_2008.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:118666","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/118666","pdf_url":"http://infoscience.epfl.ch/record/118666","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1554694706.pdf","grobid_xml":"https://content.openalex.org/works/W1554694706.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1539972817","https://openalex.org/W2084510706","https://openalex.org/W2188714255","https://openalex.org/W2050419915","https://openalex.org/W1551258999","https://openalex.org/W1964241209","https://openalex.org/W2112617223","https://openalex.org/W2574640713","https://openalex.org/W2088097596","https://openalex.org/W2465735182","https://openalex.org/W2283472011","https://openalex.org/W2128834557","https://openalex.org/W2143569040","https://openalex.org/W2152733491","https://openalex.org/W1965995772","https://openalex.org/W3190023615","https://openalex.org/W3005296017","https://openalex.org/W155594457","https://openalex.org/W2084631479","https://openalex.org/W267875035"],"abstract_inverted_index":{"In":[0,69,281,513,700],"this":[1,224,282,555,583,615,640],"thesis,":[2,519],"we":[3,16,74,239,284,324,366,394,520,553],"explore":[4],"the":[5,30,53,58,62,67,130,174,188,229,275,290,296,305,397,405,408,419,437,452,464,491,514,518,523,528,536,542,564,569,573,576,580,590,593,597,629,634,659,667,675],"use":[6],"of":[7,142,163,173,183,223,232,274,310,334,346,421,494,517,538,544,661,669,677],"machine":[8,71,643],"learning":[9,72,79,113,231,262,267,327,391,430,445,448,484,493,644,651,688],"techniques":[10],"for":[11,132,147,168,447,510,633,646,653],"information":[12,378,399],"retrieval.":[13,280,648],"More":[14],"specifically,":[15],"focus":[17],"on":[18,244,259,278,343,370,476,490,686],"ad-hoc":[19,49,177,212,233,409,647],"retrieval,":[20],"which":[21,127,503,694],"is":[22,38,123,214,226,339,380,387,606,621],"concerned":[23],"with":[24,160,348,471,624,704],"searching":[25],"large":[26,218,269],"corpora":[27],"to":[28,33,61,90,95,111,180,195,200,217,227,251,289,300,304,329,360,368,382,403,436,451,535,609,614],"identify":[29,91,330],"documents":[31,59,102,165,197,298,663],"relevant":[32,60,164,351,381],"user":[34,46],"queries.":[35,104,202,425],"This":[36,105,337,385,440,456,468,497,604,619],"identification":[37,338],"performed":[39,341],"through":[40],"a":[41,45,70,92,124,133,140,156,161,169,181,286,317,326,344,389,429,433,558,562,611,625],"ranking":[42,125,292,438,460,559],"task.":[43,411,481,637],"Given":[44],"query,":[47],"an":[48,143,331,458,477,499,586],"retrieval":[50,98,153,178,213,234,253,291,410,416,420,454,465,530,636,656,660,668,676],"system":[51],"ranks":[52],"corpus":[54,149],"documents,":[55],"so":[56,571],"that":[57,81,129,237,264,321,379,462,474,522,551,572],"query":[63,135],"ideally":[64],"appear":[65,578],"above":[66,579],"others.":[68,581],"framework,":[73],"are":[75,357],"interested":[76],"in":[77,88,320,527,547],"proposing":[78],"algorithms":[80,263],"can":[82,504,532],"benefit":[83,395,505],"from":[84,396,423,506,628,664,671,680],"limited":[85],"training":[86,692],"data":[87,356],"order":[89,295,568],"ranker":[93],"likely":[94],"achieve":[96],"high":[97],"performance":[99,406],"over":[100,268,407],"unseen":[101],"and":[103,294,323,362,674,689,697,709],"problem":[106,466,556],"presents":[107,207],"novel":[108],"challenges":[109],"compared":[110],"traditional":[112],"tasks,":[114],"such":[115,355],"as":[116,139,557],"regression":[117],"or":[118,247],"classification.":[119],"First,":[120],"our":[121,204,443,483],"task":[122,205,537],"problem,":[126,186,293,417],"means":[128],"loss":[131,145],"given":[134,545,561],"cannot":[136],"be":[137,533],"measured":[138],"sum":[141],"individual":[144],"suffered":[146],"each":[148],"document.":[150],"Second,":[151],"most":[152,598],"queries":[154,347,673],"present":[155],"highly":[157],"unbalanced":[158],"setup,":[159,392],"set":[162,345],"accounting":[166],"only":[167,193],"very":[170],"small":[171],"fraction":[172],"corpus.":[175],"Third,":[176],"corresponds":[179],"kind":[182],"\"double\"":[184],"generalization":[185],"since":[187,211,354,373],"learned":[189,623],"model":[190,461,612,620],"should":[191,567],"not":[192,340],"generalize":[194],"new":[196,201],"but":[198],"also":[199,206],"Finally,":[203],"challenging":[208],"efficiency":[209],"constraints,":[210],"typically":[215],"applied":[216,534],"corpora.":[219,270],"The":[220,255,271,308],"main":[221],"objective":[222,446,524,587,605],"thesis":[225,276,641],"investigate":[228,414],"discriminative":[230,687],"models.":[235,699],"For":[236,550],"purpose,":[238,552],"propose":[240,325,367,650],"different":[241,252,260],"models":[242,652],"based":[243],"kernel":[245],"machines":[246],"neural":[248],"networks":[249],"adapted":[250,613],"contexts.":[254],"proposed":[256],"approaches":[257,645,684,706],"rely":[258,369,685],"online":[261,492],"allow":[265],"efficient":[266,691],"first":[272],"part":[273,516],"focuses":[277],"text":[279,297,306,314,335,424,662,665,672],"case,":[283],"adopt":[285],"classical":[287],"approach":[288,328,427,469],"according":[299],"their":[301,349],"estimated":[302],"similarity":[303,312,383,450],"query.":[307],"assessment":[309],"semantic":[311,376],"between":[313],"items":[315],"plays":[316],"key":[318],"role":[319],"setup":[322,386],"effective":[332,696],"measure":[333],"similarity.":[336],"relying":[342],"corresponding":[350],"document":[352],"sets,":[353],"especially":[358],"expensive":[359],"label":[361],"hence":[363,388],"rare.":[364],"Instead,":[365],"hyperlink":[371],"data,":[372],"hyperlinks":[374,402],"convey":[375],"proximity":[377,398],"learning.":[384],"transfer":[390],"where":[393],"encoded":[400],"by":[401],"improve":[404],"We":[412,649],"then":[413,607,622],"another":[415],"i.e.":[418,541,658],"images":[422,670],"Our":[426,683],"introduces":[428,642],"procedure":[431,485,626],"optimizing":[432],"criterion":[434,441],"related":[435],"performance.":[439],"adapts":[442],"previous":[444,472,529],"textual":[449],"image":[453,459,479,511,635],"problem.":[455,618],"yields":[457,498,585,695],"addresses":[463],"directly.":[467],"contrasts":[470],"research":[473],"relies":[475],"intermediate":[478],"annotation":[480],"Moreover,":[482],"builds":[486],"upon":[487],"recent":[488,507],"work":[489],"kernel-based":[495],"classifiers.":[496],"efficient,":[500],"scalable":[501,698],"algorithm,":[502],"kernels":[508],"developed":[509],"comparison.":[512],"last":[515],"show":[521],"function":[525],"used":[526,608],"problems":[531],"keyword":[539,565,577,600],"spotting,":[540],"detection":[543],"keywords":[546],"speech":[548,678],"utterances.":[549],"formalize":[554],"task:":[560],"keyword,":[563],"spotter":[566,601],"utterances":[570,574],"containing":[575],"Interestingly,":[582],"formulation":[584],"directly":[588],"maximizing":[589],"area":[591],"under":[592],"receiver":[594],"operating":[595],"curve,":[596],"common":[599],"evaluation":[602],"measure.":[603],"train":[610],"intrinsically":[616],"sequential":[617],"derived":[627],"algorithm":[630],"previously":[631],"introduced":[632],"To":[638],"conclude,":[639],"various":[654],"multi-modal":[655],"setups,":[657],"queries,":[666],"recordings":[679],"written":[681],"keywords.":[682],"enjoy":[690],"procedures,":[693],"all":[701],"cases,":[702],"links":[703],"prior":[705],"were":[707,712],"investigated":[708],"experimental":[710],"comparisons":[711],"conducted.":[713]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}