{"id":"https://openalex.org/W2963903950","doi":"https://doi.org/10.18653/v1/d16-1230","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","display_name":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2963903950","doi":"https://doi.org/10.18653/v1/d16-1230","mag":"2963903950"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d16-1230","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1230","pdf_url":"https://www.aclweb.org/anthology/D16-1230.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 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D16-1230.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101886983","display_name":"Chia\u2010Wei Liu","orcid":"https://orcid.org/0009-0008-8585-2718"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chia-Wei Liu","raw_affiliation_strings":["School of Computer Science, McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004295653","display_name":"Ryan Lowe","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ryan Lowe","raw_affiliation_strings":["School of Computer Science, McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034688833","display_name":"Iulian Vlad Serban","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]},{"id":"https://openalex.org/I894135719","display_name":"University of Monterrey","ror":"https://ror.org/02arnxw97","country_code":"MX","type":"education","lineage":["https://openalex.org/I894135719"]}],"countries":["CA","MX"],"is_corresponding":false,"raw_author_name":"Iulian Serban","raw_affiliation_strings":["DIRO, Universit de Montral","DIRO, Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIRO, Universit de Montral","institution_ids":["https://openalex.org/I894135719"]},{"raw_affiliation_string":"DIRO, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mike Noseworthy","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mike Noseworthy","raw_affiliation_strings":["School of Computer Science, McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066769688","display_name":"Laurent Charlin","orcid":"https://orcid.org/0000-0002-6545-9459"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Laurent Charlin","raw_affiliation_strings":["School of Computer Science, McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["School of Computer Science, McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":54.9385,"has_fulltext":true,"cited_by_count":919,"citation_normalized_percentile":{"value":0.99899942,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2122","last_page":"2132"},"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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":0.7251676321029663},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5003767013549805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4469677805900574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36521679162979126},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34888148307800293},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08765086531639099},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07481527328491211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251676321029663},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5003767013549805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4469677805900574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36521679162979126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34888148307800293},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08765086531639099},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07481527328491211}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d16-1230","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1230","pdf_url":"https://www.aclweb.org/anthology/D16-1230.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 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d16-1230","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1230","pdf_url":"https://www.aclweb.org/anthology/D16-1230.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 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963903950.pdf","grobid_xml":"https://content.openalex.org/works/W2963903950.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W10957333","https://openalex.org/W119047706","https://openalex.org/W137851535","https://openalex.org/W836999996","https://openalex.org/W1486649854","https://openalex.org/W1489525520","https://openalex.org/W1518951372","https://openalex.org/W1552182777","https://openalex.org/W1591706642","https://openalex.org/W1654173042","https://openalex.org/W1810943226","https://openalex.org/W1948566616","https://openalex.org/W1958706068","https://openalex.org/W1982897610","https://openalex.org/W1983578042","https://openalex.org/W2001810881","https://openalex.org/W2037789405","https://openalex.org/W2065687817","https://openalex.org/W2087735403","https://openalex.org/W2089150068","https://openalex.org/W2101105183","https://openalex.org/W2102672872","https://openalex.org/W2107667213","https://openalex.org/W2111151330","https://openalex.org/W2123301721","https://openalex.org/W2123891489","https://openalex.org/W2137607259","https://openalex.org/W2143177362","https://openalex.org/W2151814822","https://openalex.org/W2153579005","https://openalex.org/W2154652894","https://openalex.org/W2159107349","https://openalex.org/W2250645967","https://openalex.org/W2251994258","https://openalex.org/W2257408573","https://openalex.org/W2294699749","https://openalex.org/W2603612888","https://openalex.org/W2895810819","https://openalex.org/W2950483141","https://openalex.org/W2951813108","https://openalex.org/W2962854379","https://openalex.org/W2962883855","https://openalex.org/W2963206148","https://openalex.org/W2963499246","https://openalex.org/W2963790827","https://openalex.org/W2964352131","https://openalex.org/W3022187094","https://openalex.org/W4211147687","https://openalex.org/W4252434862","https://openalex.org/W4294170691","https://openalex.org/W4295803813"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4205958290","https://openalex.org/W2789919619"],"abstract_inverted_index":{"We":[0,41,66],"investigate":[1],"evaluation":[2,87],"metrics":[3,26,45,88],"for":[4,81,89],"dialogue":[5,90],"response":[6,22,35],"generation":[7,23],"systems":[8],"where":[9],"supervised":[10],"labels,":[11],"such":[12],"as":[13],"task":[14],"completion,":[15],"are":[16],"not":[17,58],"available.":[18],"Recent":[19],"works":[20],"in":[21,52,61,75],"have":[24],"adopted":[25],"from":[27],"machine":[28],"translation":[29],"to":[30,36],"compare":[31],"a":[32,37],"model's":[33],"generated":[34],"single":[38],"target":[39],"response.":[40],"show":[42],"that":[43],"these":[44],"correlate":[46],"very":[47],"weakly":[48],"with":[49],"human":[50],"judgements":[51],"the":[53,62],"non-technical":[54],"Twitter":[55],"domain,":[56],"and":[57,69,78],"at":[59],"all":[60],"technical":[63],"Ubuntu":[64],"domain.":[65],"provide":[67,79],"quantitative":[68],"qualitative":[70],"results":[71],"highlighting":[72],"specific":[73],"weaknesses":[74],"existing":[76],"metrics,":[77],"recommendations":[80],"future":[82],"development":[83],"of":[84],"better":[85],"automatic":[86],"systems.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":111},{"year":2022,"cited_by_count":130},{"year":2021,"cited_by_count":141},{"year":2020,"cited_by_count":164},{"year":2019,"cited_by_count":146},{"year":2018,"cited_by_count":97},{"year":2017,"cited_by_count":38},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}