{"id":"https://openalex.org/W3114032074","doi":"https://doi.org/10.18653/v1/2020.coling-main.368","title":"Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems","display_name":"Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3114032074","doi":"https://doi.org/10.18653/v1/2020.coling-main.368","mag":"3114032074"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.coling-main.368","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.368","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.368.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.coling-main.368.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059683075","display_name":"Vitou Phy","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Vitou Phy","raw_affiliation_strings":["\u2660 The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"\u2660 The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992618","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-1028-3406"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["IBM-Research Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"IBM-Research Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041062417","display_name":"Akiko Aizawa","orcid":"https://orcid.org/0000-0001-6544-5076"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akiko Aizawa","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059683075"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":4.2523,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.95214724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4164","last_page":"4178"},"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.8199239373207092},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.722903847694397},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7051453590393066},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.6731123328208923},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5857723951339722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5713739991188049},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5699840188026428},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5441880822181702},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.5132768154144287},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5117266178131104},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47484472393989563},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4723312258720398},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45228832960128784},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4234992563724518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4074913561344147},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.09849506616592407},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09613296389579773},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0949910581111908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199239373207092},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.722903847694397},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7051453590393066},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.6731123328208923},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5857723951339722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5713739991188049},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5699840188026428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5441880822181702},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.5132768154144287},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5117266178131104},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47484472393989563},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4723312258720398},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45228832960128784},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4234992563724518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4074913561344147},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.09849506616592407},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09613296389579773},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0949910581111908},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.coling-main.368","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.368","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.368.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.coling-main.368","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.368","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.368.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327550","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3114032074.pdf","grobid_xml":"https://content.openalex.org/works/W3114032074.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1518951372","https://openalex.org/W1522301498","https://openalex.org/W1591706642","https://openalex.org/W2053154970","https://openalex.org/W2061272711","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2250645967","https://openalex.org/W2584220694","https://openalex.org/W2593751037","https://openalex.org/W2761590056","https://openalex.org/W2798888952","https://openalex.org/W2799037524","https://openalex.org/W2885421725","https://openalex.org/W2892228078","https://openalex.org/W2896457183","https://openalex.org/W2919290281","https://openalex.org/W2936695845","https://openalex.org/W2951583236","https://openalex.org/W2962784628","https://openalex.org/W2962786758","https://openalex.org/W2962883855","https://openalex.org/W2963206148","https://openalex.org/W2963341956","https://openalex.org/W2963499246","https://openalex.org/W2963527228","https://openalex.org/W2963544536","https://openalex.org/W2963903950","https://openalex.org/W2964121744","https://openalex.org/W2964178377","https://openalex.org/W2964308564","https://openalex.org/W2970603474","https://openalex.org/W2977539532","https://openalex.org/W2988937804","https://openalex.org/W2996044589","https://openalex.org/W2996403597","https://openalex.org/W3000779003","https://openalex.org/W3014461195","https://openalex.org/W3034600233","https://openalex.org/W3034808773","https://openalex.org/W3035656139","https://openalex.org/W3107013681","https://openalex.org/W3213935765","https://openalex.org/W4287900772","https://openalex.org/W4295803813"],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W1970538215","https://openalex.org/W2400151637","https://openalex.org/W2975827637","https://openalex.org/W2133478886","https://openalex.org/W4283317842","https://openalex.org/W2998494704","https://openalex.org/W2988197017","https://openalex.org/W3034808773","https://openalex.org/W3023366413"],"abstract_inverted_index":{"Many":[0],"automatic":[1],"evaluation":[2],"metrics":[3,65,155],"have":[4],"been":[5],"proposed":[6],"to":[7,41,69,100,114,153,159],"score":[8,77,181],"the":[9,19,34,42,102],"overall":[10,20],"quality":[11,21],"of":[12,24,36,139,156],"a":[13,50,59,109,115,137,145,150,161],"response":[14],"in":[15,49,58,173],"open-domain":[16],"dialogue.":[17],"Generally,":[18],"is":[22,47,56,112,136],"comprised":[23],"various":[25],"aspects,":[26,104],"such":[27,72],"as":[28],"relevancy,":[29],"specificity,":[30],"and":[31,33,92,132,171,188,195],"empathy,":[32],"importance":[35],"each":[37,157],"aspect":[38,158],"differs":[39],"according":[40],"task.":[43,146],"For":[44,74],"instance,":[45],"specificity":[46],"mandatory":[48],"food-ordering":[51],"dialogue":[52,61],"task,":[53,116],"whereas":[54,84],"fluency":[55],"preferred":[57],"language-teaching":[60],"system.":[62],"However,":[63],"existing":[64],"are":[66,97,142],"not":[67,98],"designed":[68],"cope":[70],"with":[71,185],"flexibility.":[73],"example,":[75],"BLEU":[76],"fundamentally":[78],"relies":[79,86],"only":[80],"on":[81,87],"word":[82],"overlapping,":[83],"BERTScore":[85],"semantic":[88],"similarity":[89],"between":[90],"reference":[91],"candidate":[93],"response.":[94],"Thus,":[95],"they":[96],"guaranteed":[99],"capture":[101],"required":[103],"i.e.,":[105],"specificity.":[106],"To":[107],"design":[108],"metric":[110,163],"that":[111,141,179],"flexible":[113],"we":[117],"first":[118],"propose":[119,149],"making":[120],"these":[121],"qualities":[122,140],"manageable":[123],"by":[124],"grouping":[125],"them":[126],"into":[127],"three":[128],"groups:":[129],"understandability,":[130],"sensibleness,":[131],"likability,":[133],"where":[134],"likability":[135],"combination":[138],"essential":[143],"for":[144,168],"We":[147,177],"also":[148],"simple":[151],"method":[152],"composite":[154],"obtain":[160],"single":[162],"called":[164],"USL-H,":[165],"which":[166],"stands":[167],"Understandability,":[169],"Sensibleness,":[170],"Likability":[172],"Hierarchy":[174],"1":[175],".":[176],"demonstrated":[178],"USL-H":[180],"achieves":[182],"good":[183],"correlations":[184],"human":[186],"judgment":[187],"maintains":[189],"its":[190],"configurability":[191],"towards":[192],"different":[193],"aspects":[194],"metrics.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}