{"id":"https://openalex.org/W2986867746","doi":"https://doi.org/10.1145/3357384.3357889","title":"Enhancing Conversational Dialogue Models with Grounded Knowledge","display_name":"Enhancing Conversational Dialogue Models with Grounded Knowledge","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2986867746","doi":"https://doi.org/10.1145/3357384.3357889","mag":"2986867746"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3357889","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3357889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","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/A5035367145","display_name":"Wen Zheng","orcid":"https://orcid.org/0000-0002-6570-6245"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Wen Zheng","raw_affiliation_strings":["University of Nottingham, Nottingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Nottingham, Nottingham, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101500495","display_name":"Ke Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]},{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ke Zhou","raw_affiliation_strings":["University of Nottingham & Nokia Bell Labs, Nottingham & Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Nottingham & Nokia Bell Labs, Nottingham & Cambridge, United Kingdom","institution_ids":["https://openalex.org/I142263535","https://openalex.org/I4210098141"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035367145"],"corresponding_institution_ids":["https://openalex.org/I142263535"],"apc_list":null,"apc_paid":null,"fwci":2.1002,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90512053,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"709","last_page":"718"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9962000250816345,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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":0.7973269820213318},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7619204521179199},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.632308304309845},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4894174635410309},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4416128098964691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4215211272239685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3764888048171997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973269820213318},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7619204521179199},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.632308304309845},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4894174635410309},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4416128098964691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4215211272239685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3764888048171997},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357384.3357889","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3357889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1993378086","https://openalex.org/W2133459682","https://openalex.org/W2250539671","https://openalex.org/W2579486552","https://openalex.org/W2734443755","https://openalex.org/W2741363662","https://openalex.org/W2798392716","https://openalex.org/W2885421725","https://openalex.org/W2904631866","https://openalex.org/W2907833097","https://openalex.org/W2949888546","https://openalex.org/W2963206148","https://openalex.org/W2963403868","https://openalex.org/W2963789888","https://openalex.org/W2964110616","https://openalex.org/W2964210218","https://openalex.org/W2964308564","https://openalex.org/W3011801489","https://openalex.org/W3101567279","https://openalex.org/W6691431627"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4237784285","https://openalex.org/W4390549206","https://openalex.org/W4390718435","https://openalex.org/W3137171911","https://openalex.org/W4248905757","https://openalex.org/W2374712251","https://openalex.org/W4383031710","https://openalex.org/W2386000789","https://openalex.org/W4379540039"],"abstract_inverted_index":{"Leveraging":[0],"external":[1,55,127,135],"knowledge":[2,44,56],"to":[3,17,41,66,84],"enhance":[4,67],"conversational":[5,69,97,116],"models":[6,23,117,173],"has":[7],"become":[8],"a":[9,139],"popular":[10],"research":[11,48],"area":[12],"in":[13,37,79,174],"recent":[14],"years.":[15],"Compared":[16],"vanilla":[18],"generative":[19],"models,":[20,98],"the":[21,38,63,68,86,123,154],"knowledge-grounded":[22,96],"may":[24],"produce":[25],"more":[26],"informative":[27],"and":[28,60,76,107,179],"engaging":[29],"responses.":[30,163],"Although":[31],"various":[32,92],"approaches":[33],"have":[34],"been":[35],"proposed":[36,169],"past,":[39],"how":[40,53],"effectively":[42,130],"incorporate":[43],"remains":[45],"an":[46],"open":[47],"question.":[49],"It":[50],"is":[51,62],"unclear":[52],"much":[54],"should":[57],"be":[58,120],"retrieved":[59],"what":[61],"optimal":[64],"way":[65],"model,":[70],"trading":[71],"off":[72],"between":[73],"relevant":[74],"information":[75,132],"noise.":[77],"Therefore,":[78],"this":[80],"paper,":[81],"we":[82,137],"aim":[83],"bridge":[85],"gap":[87],"by":[88],"first":[89],"extensively":[90],"evaluating":[91],"types":[93],"of":[94,126,159,176],"state-of-the-art":[95,172],"including":[99],"recurrent":[100],"neural":[101],"network":[102],"based,":[103,106],"memory":[104],"networks":[105],"Transformer":[108,141],"based":[109],"models.":[110],"We":[111],"demonstrate":[112],"empirically":[113],"that":[114,167],"those":[115],"can":[118,151],"only":[119],"enhanced":[121],"with":[122,142],"right":[124],"amount":[125],"knowledge.":[128],"To":[129],"leverage":[131],"originated":[133],"from":[134],"knowledge,":[136],"propose":[138],"novel":[140],"Expanded":[143],"Decoder":[144],"(Transformer-ED":[145],"or":[146],"TED":[147],"for":[148,156],"short),":[149],"which":[150],"automatically":[152],"tune":[153],"weights":[155],"different":[157],"sources":[158],"evidence":[160],"when":[161],"generating":[162],"Our":[164],"experiments":[165],"show":[166],"our":[168],"model":[170],"outperforms":[171],"terms":[175],"both":[177],"quality":[178],"diversity.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}