{"id":"https://openalex.org/W2953171463","doi":"https://doi.org/10.1145/3292500.3330754","title":"Generating Better Search Engine Text Advertisements with Deep Reinforcement Learning","display_name":"Generating Better Search Engine Text Advertisements with Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2953171463","doi":"https://doi.org/10.1145/3292500.3330754","mag":"2953171463"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330754","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330754","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330754","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330754","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033073989","display_name":"J. Weston Hughes","orcid":"https://orcid.org/0000-0002-7042-4031"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. Weston Hughes","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103647697","display_name":"Keng-hao Chang","orcid":null},"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":"Keng-hao Chang","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046102901","display_name":"Ruofei Zhang","orcid":"https://orcid.org/0000-0002-4063-0109"},"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":"Ruofei Zhang","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033073989"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":3.9205,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94933214,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2269","last_page":"2277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9947999715805054,"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/T10260","display_name":"Software Engineering Research","score":0.9891999959945679,"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":0.7735118865966797},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.767839789390564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6438442468643188},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5608904361724854},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5192410945892334},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49064674973487854},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.480229914188385},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45502880215644836},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4534655809402466},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4125528037548065},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40274351835250854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.374866247177124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735118865966797},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.767839789390564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6438442468643188},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5608904361724854},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5192410945892334},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49064674973487854},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.480229914188385},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45502880215644836},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4534655809402466},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4125528037548065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40274351835250854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.374866247177124},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330754","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330754","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330754","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330754","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330754","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330754","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953171463.pdf","grobid_xml":"https://content.openalex.org/works/W2953171463.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W101212897","https://openalex.org/W1522301498","https://openalex.org/W1570168312","https://openalex.org/W1843891098","https://openalex.org/W1977664850","https://openalex.org/W2001528886","https://openalex.org/W2064987260","https://openalex.org/W2066158919","https://openalex.org/W2090883204","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2154652894","https://openalex.org/W2333611780","https://openalex.org/W2475287302","https://openalex.org/W2509593407","https://openalex.org/W2512965516","https://openalex.org/W2525778437","https://openalex.org/W2560313346","https://openalex.org/W2606974598","https://openalex.org/W2610314927","https://openalex.org/W2797269287","https://openalex.org/W2949335953","https://openalex.org/W2949888546","https://openalex.org/W2952138241","https://openalex.org/W2952782394","https://openalex.org/W3098269892"],"related_works":["https://openalex.org/W4284703357","https://openalex.org/W4281385036","https://openalex.org/W2058999950","https://openalex.org/W2525579390","https://openalex.org/W2129683077","https://openalex.org/W4380075502","https://openalex.org/W4287887250","https://openalex.org/W4226126415","https://openalex.org/W2251089395","https://openalex.org/W4288804510"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"has":[3,31],"been":[4,33],"applied":[5,34],"in":[6,18,49,144,151],"a":[7,67,83,98,141,148],"number":[8],"of":[9,44,61,107],"fields":[10],"to":[11,20,35,41,69,77,81,88,100,115],"directly":[12],"optimize":[13],"non-differentiable":[14],"reward":[15],"functions,":[16],"including":[17],"sequence":[19,21,68,70,114,116],"settings":[22],"using":[23,112,134],"Self":[24],"Critical":[25],"Sequence":[26],"Training":[27],"(SCST).":[28],"Previously,":[29],"SCST":[30,158],"primarily":[32],"bring":[36],"conditional":[37],"language":[38],"models":[39],"closer":[40],"the":[42,59,122],"distribution":[43],"their":[45],"training":[46,117,138,159],"set,":[47],"as":[48,66,127],"traditional":[50],"neural":[51],"machine":[52],"translation":[53],"and":[54,72,87],"abstractive":[55],"summarization.":[56],"We":[57,95],"frame":[58],"generation":[60],"search":[62],"engine":[63],"text":[64],"ads":[65,79,90,164],"problem,":[71],"consider":[73],"two":[74],"related":[75],"goals:":[76],"generate":[78,89],"similar":[80],"those":[82],"human":[84],"would":[85],"write,":[86],"with":[91],"high":[92],"click-through":[93,124],"rates.":[94],"jointly":[96],"train":[97],"model":[99,133],"minimize":[101],"cross-entropy":[102],"on":[103],"an":[104,130],"existing":[105,131],"corpus":[106],"Landing":[108],"Page/Text":[109],"Ad":[110],"pairs":[111],"typical":[113],"techniques":[118],"while":[119],"also":[120],"optimizing":[121],"expected":[123,145],"rate":[125],"(CTR)":[126],"predicted":[128],"by":[129],"oracle":[132],"SCST.":[135],"Through":[136],"joint":[137],"we":[139],"achieve":[140],"6.7%":[142],"increase":[143],"CTR":[146],"without":[147,165],"meaningful":[149],"drop":[150],"ROUGE":[152],"score.":[153],"Human":[154],"experiments":[155],"demonstrate":[156],"that":[157],"produces":[160],"significantly":[161],"more":[162],"attractive":[163],"reducing":[166],"grammatical":[167],"quality.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}