{"id":"https://openalex.org/W3089172967","doi":"https://doi.org/10.1145/3387940.3391465","title":"Evaluating Surprise Adequacy for Question Answering","display_name":"Evaluating Surprise Adequacy for Question Answering","publication_year":2020,"publication_date":"2020-06-27","ids":{"openalex":"https://openalex.org/W3089172967","doi":"https://doi.org/10.1145/3387940.3391465","mag":"3089172967"},"language":"en","primary_location":{"id":"doi:10.1145/3387940.3391465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3387940.3391465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops","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/A5027053870","display_name":"Seah Kim","orcid":"https://orcid.org/0000-0002-9581-1222"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seah Kim","raw_affiliation_strings":["School of Computing, KAIST Daejon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, KAIST Daejon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070401254","display_name":"Shin Yoo","orcid":"https://orcid.org/0000-0002-0836-6993"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shin Yoo","raw_affiliation_strings":["School of Computing, KAIST Daejon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, KAIST Daejon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.3544,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85511491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9958999752998352,"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/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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":0.8121825456619263},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.7933591604232788},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7929445505142212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6860055327415466},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6718859076499939},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6416798233985901},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5906844139099121},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5400505661964417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5110145807266235},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5019609928131104},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4797000586986542},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4451373219490051},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4205020070075989},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11062926054000854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121825456619263},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.7933591604232788},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7929445505142212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6860055327415466},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6718859076499939},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6416798233985901},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5906844139099121},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5400505661964417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5110145807266235},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5019609928131104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4797000586986542},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4451373219490051},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4205020070075989},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11062926054000854},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3387940.3391465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3387940.3391465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3338737308","display_name":null,"funder_award_id":"NRF-2018R1A5A1059921","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4400926266","display_name":null,"funder_award_id":"1711073912","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2022508996","https://openalex.org/W2097117768","https://openalex.org/W2119112357","https://openalex.org/W2592929672","https://openalex.org/W2616028256","https://openalex.org/W2804337238","https://openalex.org/W2954629067","https://openalex.org/W2963327228","https://openalex.org/W3099444373","https://openalex.org/W4212774754","https://openalex.org/W4253343410"],"related_works":["https://openalex.org/W4236382845","https://openalex.org/W4388712630","https://openalex.org/W2481168998","https://openalex.org/W2476994687","https://openalex.org/W642988558","https://openalex.org/W2324507472","https://openalex.org/W2511141457","https://openalex.org/W1999899047","https://openalex.org/W2173353921","https://openalex.org/W2810824260"],"abstract_inverted_index":{"With":[0],"the":[1,33,49,52,80,95,99,109,117,137],"wide":[2],"and":[3],"rapid":[4],"adoption":[5],"of":[6,32,111],"Deep":[7],"Neural":[8,71],"Networks":[9,72],"(DNNs)":[10],"in":[11,24,92],"various":[12,25],"domains,":[13],"an":[14],"urgent":[15],"need":[16],"to":[17,39,51,62,90,94,102],"validate":[18],"their":[19],"behaviour":[20],"has":[21,59,75],"risen,":[22],"resulting":[23],"test":[26,133],"adequacy":[27,134],"metrics":[28],"for":[29,55,65,79,136],"DNNs.":[30],"One":[31],"metrics,":[34],"Surprise":[35],"Adequacy":[36],"(SA),":[37],"aims":[38],"measure":[40],"how":[41],"surprising":[42],"a":[43,132],"new":[44],"input":[45],"is":[46,101],"based":[47,68],"on":[48,69],"similarity":[50],"data":[53],"used":[54,119],"training.":[56],"While":[57],"SA":[58,89,105,127],"been":[60,77],"evaluated":[61],"be":[63],"effective":[64],"image":[66],"classifiers":[67],"Convolutional":[70],"(CNNs),":[73],"it":[74],"not":[76],"studied":[78],"Natural":[81],"Language":[82],"Processing":[83],"(NLP)":[84],"domain.":[85],"This":[86],"paper":[87],"applies":[88],"NLP,":[91],"particular":[93],"question":[96,138],"answering":[97,139],"task:":[98],"aim":[100],"investigate":[103],"whether":[104],"correlates":[106],"well":[107,130],"with":[108],"correctness":[110],"answers.":[112],"An":[113],"empirical":[114],"evaluation":[115],"using":[116],"widely":[118],"Stanford":[120],"Question":[121],"Answering":[122],"Dataset":[123],"(SQuAD)":[124],"shows":[125],"that":[126],"can":[128],"work":[129],"as":[131],"metric":[135],"task.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}