{"id":"https://openalex.org/W2975606059","doi":"https://doi.org/10.1145/3341981.3344220","title":"Learning a Better Negative Sampling Policy with Deep Neural Networks for Search","display_name":"Learning a Better Negative Sampling Policy with Deep Neural Networks for Search","publication_year":2019,"publication_date":"2019-09-26","ids":{"openalex":"https://openalex.org/W2975606059","doi":"https://doi.org/10.1145/3341981.3344220","mag":"2975606059"},"language":"en","primary_location":{"id":"doi:10.1145/3341981.3344220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341981.3344220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of 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/A5082506991","display_name":"Daniel J. Cohen","orcid":"https://orcid.org/0000-0001-5819-1135"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Cohen","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102878835","display_name":"Scott M. Jordan","orcid":"https://orcid.org/0000-0003-3329-6998"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott M. Jordan","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105659698","display_name":"W. Bruce Croft","orcid":"https://orcid.org/0000-0003-2391-9629"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Bruce Croft","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082506991"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.2601,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85344303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8834108114242554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7950843572616577},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7259676456451416},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6951687335968018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6769716143608093},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6516655683517456},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6245779991149902},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5826728343963623},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5676122307777405},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5565499663352966},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5280492901802063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5069642066955566},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47904717922210693},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47543075680732727},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4344971477985382},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4222719669342041},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33027923107147217},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08517000079154968}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8834108114242554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950843572616577},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7259676456451416},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6951687335968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6769716143608093},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6516655683517456},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6245779991149902},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5826728343963623},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5676122307777405},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5565499663352966},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5280492901802063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5069642066955566},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47904717922210693},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47543075680732727},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4344971477985382},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4222719669342041},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33027923107147217},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08517000079154968},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3341981.3344220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341981.3344220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1484084878","https://openalex.org/W1514587017","https://openalex.org/W1777239053","https://openalex.org/W2093390569","https://openalex.org/W2097732278","https://openalex.org/W2100664567","https://openalex.org/W2102035799","https://openalex.org/W2107726111","https://openalex.org/W2119717200","https://openalex.org/W2121492055","https://openalex.org/W2131571251","https://openalex.org/W2155027007","https://openalex.org/W2251202616","https://openalex.org/W2286300105","https://openalex.org/W2342840547","https://openalex.org/W2515565210","https://openalex.org/W2519314406","https://openalex.org/W2539671052","https://openalex.org/W2553303224","https://openalex.org/W2610935556","https://openalex.org/W2619206542","https://openalex.org/W2619307294","https://openalex.org/W2725049817","https://openalex.org/W2736601468","https://openalex.org/W2753300133","https://openalex.org/W2786471719","https://openalex.org/W2919347051","https://openalex.org/W2949989304","https://openalex.org/W2950075229","https://openalex.org/W2951603627","https://openalex.org/W2962997783","https://openalex.org/W2964005754","https://openalex.org/W2964327384","https://openalex.org/W3101023724","https://openalex.org/W3101997094","https://openalex.org/W3118608800","https://openalex.org/W3212575067","https://openalex.org/W6600339963"],"related_works":["https://openalex.org/W4298369531","https://openalex.org/W3155135229","https://openalex.org/W4281847915","https://openalex.org/W3208882810","https://openalex.org/W2972862903","https://openalex.org/W3099765033","https://openalex.org/W2921259037","https://openalex.org/W2970699417","https://openalex.org/W4288419306","https://openalex.org/W2987302549"],"abstract_inverted_index":{"In":[0,81],"information":[1],"retrieval,":[2],"sampling":[3,43,71,126],"methods":[4],"used":[5],"to":[6,33,90,118,138,144],"select":[7],"documents":[8,93],"for":[9],"neural":[10,31],"models":[11,32],"must":[12],"often":[13],"deal":[14],"with":[15,58,75,136],"large":[16],"class":[17],"imbalances":[18],"during":[19,94],"training.":[20],"This":[21],"issue":[22],"necessitates":[23],"careful":[24],"selection":[25],"of":[26,37,51,104,125],"negative":[27,92],"instances":[28],"when":[29],"training":[30,95,134],"avoid":[34],"the":[35,76,87,102],"risk":[36],"overfitting.":[38],"For":[39],"most":[40],"work,":[41],"heuristic":[42],"approaches,":[44],"or":[45,62],"policies,":[46],"are":[47,73],"created":[48],"based":[49],"off":[50],"domain":[52],"experts,":[53],"such":[54],"as":[55,106,108],"choosing":[56],"samples":[57],"high":[59],"BM25":[60],"scores":[61],"a":[63,97,120,123],"random":[64,147],"process":[65],"over":[66,122,132],"candidate":[67],"documents.":[68],"However,":[69],"these":[70],"approaches":[72],"done":[74],"test":[77],"distribution":[78],"in":[79,100],"mind.":[80],"this":[82],"paper,":[83],"we":[84,112],"demonstrate":[85],"that":[86,114],"method":[88],"chosen":[89],"sample":[91],"plays":[96],"critical":[98],"role":[99],"both":[101],"stability":[103],"training,":[105],"well":[107],"overall":[109],"performance.":[110],"Furthermore,":[111],"establish":[113],"using":[115],"reinforcement":[116],"learning":[117],"optimize":[119],"policy":[121],"set":[124],"functions":[127],"can":[128],"significantly":[129],"improve":[130],"performance":[131],"standard":[133],"practices":[135],"respect":[137],"IR":[139],"metrics":[140],"and":[141,146],"is":[142],"robust":[143],"hyperparameters":[145],"seeds.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}