{"id":"https://openalex.org/W2963326483","doi":"https://doi.org/10.18653/v1/w19-5944","title":"Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References","display_name":"Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2963326483","doi":"https://doi.org/10.18653/v1/w19-5944","mag":"2963326483"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5944","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5944","pdf_url":"https://www.aclweb.org/anthology/W19-5944.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5944.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101920554","display_name":"Prakhar Gupta","orcid":"https://orcid.org/0000-0003-1157-1557"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prakhar Gupta","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014641065","display_name":"Shikib Mehri","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shikib Mehri","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114246802","display_name":"Tiancheng Zhao","orcid":"https://orcid.org/0000-0002-7443-0666"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiancheng Zhao","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014816733","display_name":"Amy Pavel","orcid":"https://orcid.org/0000-0002-3908-4366"},"institutions":[{"id":"https://openalex.org/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Amy Pavel","raw_affiliation_strings":["Human-Computer Interaction Institute, Carnegie Mellon University,","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Computer Interaction Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I4210128676","https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077285164","display_name":"Maxine Esk\u00e9nazi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxine Eskenazi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082603621","display_name":"Jeffrey P. Bigham","orcid":"https://orcid.org/0000-0002-2072-0625"},"institutions":[{"id":"https://openalex.org/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Jeffrey Bigham","raw_affiliation_strings":["Human-Computer Interaction Institute, Carnegie Mellon University,","Language Technologies Institute, Carnegie Mellon University,","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Computer Interaction Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I4210128676","https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5907,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87747617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"379","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/dialog-box","display_name":"Dialog box","score":0.8777786493301392},{"id":"https://openalex.org/keywords/judgement","display_name":"Judgement","score":0.8398374915122986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7870453000068665},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6534005999565125},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6237077116966248},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.5852113366127014},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4590557813644409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4407929480075836},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.423420786857605},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4193558096885681},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3862546682357788},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36769944429397583},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09997767210006714},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0941028892993927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.077879399061203}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8777786493301392},{"id":"https://openalex.org/C2776548248","wikidata":"https://www.wikidata.org/wiki/Q12621536","display_name":"Judgement","level":2,"score":0.8398374915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870453000068665},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6534005999565125},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6237077116966248},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.5852113366127014},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4590557813644409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4407929480075836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.423420786857605},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4193558096885681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3862546682357788},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36769944429397583},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09997767210006714},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0941028892993927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.077879399061203},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-5944","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5944","pdf_url":"https://www.aclweb.org/anthology/W19-5944.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.10568","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.10568","pdf_url":"https://arxiv.org/pdf/1907.10568","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2963326483","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1907.10568","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.10568","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.10568","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5944","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5944","pdf_url":"https://www.aclweb.org/anthology/W19-5944.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4937384496","display_name":null,"funder_award_id":"IIS-1816012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6378799809","display_name":"CHS: Small: Deep Integration of Crowds and AI for Robust, Scalable, and Privacy-Preserving Conversational Assistance","funder_award_id":"1816012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963326483.pdf","grobid_xml":"https://content.openalex.org/works/W2963326483.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W10957333","https://openalex.org/W1486649854","https://openalex.org/W1591706642","https://openalex.org/W2037789405","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2133512280","https://openalex.org/W2140054881","https://openalex.org/W2154652894","https://openalex.org/W2175723921","https://openalex.org/W2250484373","https://openalex.org/W2250645967","https://openalex.org/W2328886022","https://openalex.org/W2410983263","https://openalex.org/W2586847566","https://openalex.org/W2729046720","https://openalex.org/W2803947001","https://openalex.org/W2885721522","https://openalex.org/W2898658996","https://openalex.org/W2941169998","https://openalex.org/W2950658257","https://openalex.org/W2951813108","https://openalex.org/W2951883832","https://openalex.org/W2952612146","https://openalex.org/W2962717182","https://openalex.org/W2962854379","https://openalex.org/W2962883855","https://openalex.org/W2963090765","https://openalex.org/W2963206148","https://openalex.org/W2963223306","https://openalex.org/W2963456134","https://openalex.org/W2963527228","https://openalex.org/W2963544536","https://openalex.org/W2963790827","https://openalex.org/W2964178377","https://openalex.org/W2964308564","https://openalex.org/W2964352131","https://openalex.org/W2984520708","https://openalex.org/W3104405162"],"related_works":["https://openalex.org/W2979702391","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2963527228","https://openalex.org/W2250645967","https://openalex.org/W2964178377","https://openalex.org/W2963341956","https://openalex.org/W2328886022","https://openalex.org/W3166623466","https://openalex.org/W2963403868","https://openalex.org/W2962883855","https://openalex.org/W2951813108","https://openalex.org/W2250222249","https://openalex.org/W1494186835","https://openalex.org/W1487619023","https://openalex.org/W2476919256","https://openalex.org/W2798663534","https://openalex.org/W3208410661","https://openalex.org/W605591440","https://openalex.org/W3012985781"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,10,13,55,63,70,76,97],"this":[3],"paper":[4],"is":[5,37],"to":[6,25,38],"mitigate":[7],"the":[8,53,60,74,92,95],"shortcomings":[9],"automatic":[11,85],"evaluation":[12],"open-domain":[14,33],"dialog":[15],"systems":[16],"through":[17],"multireference":[18],"evaluation.":[19],"Existing":[20],"metrics":[21,86],"have":[22],"been":[23],"shown":[24],"correlate":[26],"poorly":[27],"with":[28,65],"human":[29,40,88],"judgement,":[30],"particularly":[31],"in":[32,80],"dialog.":[34],"One":[35],"alternative":[36],"collect":[39],"annotations":[41],"for":[42,90],"evaluation,":[43,57],"which":[44],"can":[45],"be":[46],"expensive":[47],"and":[48,87,94],"time":[49],"consuming.":[50],"To":[51],"demonstrate":[52],"effectiveness":[54],"multi-reference":[56],"we":[58],"augment":[59],"test":[61],"set":[62],"DailyDialog":[64],"multiple":[66,77],"references.":[67],"A":[68],"series":[69],"experiments":[71],"show":[72],"that":[73],"use":[75],"references":[78],"results":[79],"improved":[81],"correlation":[82],"between":[83],"several":[84],"judgement":[89],"both":[91],"quality":[93],"diversity":[96],"system":[98],"output.":[99]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
