{"id":"https://openalex.org/W3212613688","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.418","title":"Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness","display_name":"Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3212613688","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.418","mag":"3212613688"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.emnlp-main.418","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.418","pdf_url":"https://aclanthology.org/2021.emnlp-main.418.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.418.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085578723","display_name":"Hengtong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]},{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hengtong Zhang","raw_affiliation_strings":["Purdue University,","University at Buffalo,"],"affiliations":[{"raw_affiliation_string":"Purdue University,","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"University at Buffalo,","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091687257","display_name":"Tianhang Zheng","orcid":"https://orcid.org/0000-0002-5151-1527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianhang Zheng","raw_affiliation_strings":["Toronto University,"],"affiliations":[{"raw_affiliation_string":"Toronto University,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046576694","display_name":"Yaliang Li","orcid":"https://orcid.org/0000-0002-4204-6096"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaliang Li","raw_affiliation_strings":["Alibaba Group,"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781385","display_name":"Jing Gao","orcid":"https://orcid.org/0000-0001-5099-6991"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Gao","raw_affiliation_strings":["Purdue University,"],"affiliations":[{"raw_affiliation_string":"Purdue University,","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732938","display_name":"L\u00fc Su","orcid":"https://orcid.org/0000-0001-7223-543X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Su","raw_affiliation_strings":["Purdue University,"],"affiliations":[{"raw_affiliation_string":"Purdue University,","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100374506","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-2083-9105"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085578723"],"corresponding_institution_ids":["https://openalex.org/I219193219","https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1280037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5151","last_page":"5161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9909999966621399,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9909999966621399,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9897000193595886,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9513999819755554,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/robustness","display_name":"Robustness (evolution)","score":0.798362135887146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.79702228307724},{"id":"https://openalex.org/keywords/certification","display_name":"Certification","score":0.6343668103218079},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6290854811668396},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49612101912498474},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4933728277683258},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.49303290247917175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4551423192024231},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38599130511283875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3213593363761902},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3144657015800476}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.798362135887146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79702228307724},{"id":"https://openalex.org/C46304622","wikidata":"https://www.wikidata.org/wiki/Q374814","display_name":"Certification","level":2,"score":0.6343668103218079},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6290854811668396},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49612101912498474},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4933728277683258},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.49303290247917175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4551423192024231},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38599130511283875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3213593363761902},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3144657015800476},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2021.emnlp-main.418","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.418","pdf_url":"https://aclanthology.org/2021.emnlp-main.418.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.emnlp-main.418","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.418","pdf_url":"https://aclanthology.org/2021.emnlp-main.418.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G1606807384","display_name":"CAREER: Mining Reliable Information from Crowdsourced Data","funder_award_id":"1553411","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7659938461","display_name":null,"funder_award_id":"IIS-1553411","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3212613688.pdf","grobid_xml":"https://content.openalex.org/works/W3212613688.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W78136081","https://openalex.org/W1840435438","https://openalex.org/W1871142974","https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133564696","https://openalex.org/W2149741699","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2181854537","https://openalex.org/W2212703438","https://openalex.org/W2216854803","https://openalex.org/W2740168486","https://openalex.org/W2741229899","https://openalex.org/W2754049786","https://openalex.org/W2766108848","https://openalex.org/W2786163515","https://openalex.org/W2786977288","https://openalex.org/W2789524546","https://openalex.org/W2790153292","https://openalex.org/W2887782043","https://openalex.org/W2890472662","https://openalex.org/W2949128310","https://openalex.org/W2950048339","https://openalex.org/W2951735139","https://openalex.org/W2962756933","https://openalex.org/W2962818281","https://openalex.org/W2963266340","https://openalex.org/W2963403868","https://openalex.org/W2963446316","https://openalex.org/W2963496101","https://openalex.org/W2963565751","https://openalex.org/W2963626025","https://openalex.org/W2963667126","https://openalex.org/W2963859254","https://openalex.org/W2963952467","https://openalex.org/W2963969878","https://openalex.org/W2964253222","https://openalex.org/W2964308564","https://openalex.org/W2969662548","https://openalex.org/W2971109239","https://openalex.org/W2996851481","https://openalex.org/W2998277219","https://openalex.org/W2998293245","https://openalex.org/W3008683143","https://openalex.org/W3013267890","https://openalex.org/W3034608990","https://openalex.org/W4230813007","https://openalex.org/W4293846201","https://openalex.org/W4294170691","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2429057255","https://openalex.org/W2187546663","https://openalex.org/W148745890","https://openalex.org/W4389670110","https://openalex.org/W2611942503","https://openalex.org/W4315621326","https://openalex.org/W2899790217","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Seq2seq":[0],"models":[1,31,44,88,129,173],"have":[2],"demonstrated":[3],"their":[4],"incredible":[5],"effectiveness":[6],"in":[7,21,114,135],"a":[8,57,79,91,101,119],"large":[9],"variety":[10],"of":[11,42,71,82,94,100,109],"applications.":[12],"However,":[13],"recent":[14],"research":[15],"has":[16],"shown":[17],"that":[18,67,147,163],"inappropriate":[19],"language":[20,110],"training":[22,58,75,103,116,121,166],"samples":[23],"and":[24,45,118,156],"well-designed":[25],"testing":[26],"cases":[27],"can":[28,149,168],"induce":[29],"seq2seq":[30,43,87,128,148],"to":[32,63,85,105,123],"output":[33],"profanity.":[34,72,95,176],"These":[35],"outputs":[36],"may":[37],"potentially":[38],"hurt":[39],"the":[40,47,65,69,107,115,139,164,171],"usability":[41],"make":[46],"end-users":[48],"feel":[49],"offended.":[50],"To":[51],"address":[52],"this":[53],"problem,":[54],"we":[55,141],"propose":[56],"framework":[59,76,97,167],"with":[60,112],"certified":[61,125],"robustness":[62,126],"eliminate":[64],"causes":[66],"trigger":[68],"generation":[70],"The":[73,96],"proposed":[74,165],"leverages":[77],"merely":[78],"short":[80],"list":[81],"profanity":[83,113],"examples":[84],"prevent":[86,170],"from":[89,174],"generating":[90,175],"broader":[92],"spectrum":[93],"is":[98],"composed":[99],"patterneliminating":[102],"component":[104,122],"suppress":[106],"impact":[108],"patterns":[111],"set,":[117],"trigger-resisting":[120],"provide":[124],"for":[127],"against":[130],"intentionally":[131],"injected":[132],"profanity-triggering":[133],"expressions":[134],"test":[136],"samples.":[137],"In":[138],"experiments,":[140],"consider":[142],"two":[143],"representative":[144],"NLP":[145,172],"tasks":[146],"be":[150],"applied":[151],"to,":[152],"i.e.,":[153],"style":[154],"transfer":[155],"dialogue":[157],"generation.":[158],"Extensive":[159],"experimental":[160],"results":[161],"show":[162],"successfully":[169]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}