{"id":"https://openalex.org/W4389520280","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.731","title":"ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection","display_name":"ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389520280","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.731"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.731","pdf_url":"https://aclanthology.org/2023.findings-emnlp.731.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-emnlp.731.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638615","display_name":"Youngwook Kim","orcid":"https://orcid.org/0000-0002-4067-6254"},"institutions":[],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngwook Kim","raw_affiliation_strings":["KT, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KT, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037304991","display_name":"Shinwoo Park","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shinwoo Park","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093457237","display_name":"Youngsoo Namgoong","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngsoo Namgoong","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077698683","display_name":"Yo-Sub Han","orcid":"https://orcid.org/0000-0002-7211-6657"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yo-Sub Han","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.352,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":1,"citation_normalized_percentile":{"value":0.606989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":68,"max":79},"biblio":{"volume":null,"issue":null,"first_page":"10964","last_page":"10980"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":1.0,"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":1.0,"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/leverage","display_name":"Leverage (statistics)","score":0.7397692},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46385643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782004},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7397692},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5495556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5304881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5094977},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47015974},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46522376},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46385643},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43618974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37219852},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.731","pdf_url":"https://aclanthology.org/2023.findings-emnlp.731.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.731","pdf_url":"https://aclanthology.org/2023.findings-emnlp.731.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.71,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":32,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W2181854537","https://openalex.org/W2187089797","https://openalex.org/W2741065173","https://openalex.org/W2803765190","https://openalex.org/W2811056307","https://openalex.org/W2946681640","https://openalex.org/W2954479967","https://openalex.org/W2963341956","https://openalex.org/W2963943967","https://openalex.org/W2983342160","https://openalex.org/W2985663175","https://openalex.org/W3026526919","https://openalex.org/W3034937117","https://openalex.org/W3100081771","https://openalex.org/W3156636935","https://openalex.org/W3175487198","https://openalex.org/W3176580738","https://openalex.org/W3185909895","https://openalex.org/W3198943295","https://openalex.org/W3201622928","https://openalex.org/W3207166518","https://openalex.org/W4230541727","https://openalex.org/W4285210452","https://openalex.org/W4287692509","https://openalex.org/W4287812705","https://openalex.org/W4287888706","https://openalex.org/W4287890982","https://openalex.org/W4292779060","https://openalex.org/W4385572732","https://openalex.org/W4386566632","https://openalex.org/W4389519535"],"related_works":["https://openalex.org/W43109613","https://openalex.org/W4287644835","https://openalex.org/W3162204513","https://openalex.org/W3098003361","https://openalex.org/W3092281475","https://openalex.org/W2371138613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W2048963458"],"abstract_inverted_index":{"Implicit":[0],"hate":[1,31,40,45,105,115,184],"speech":[2,32,46,106,116],"detection":[3],"is":[4,137],"a":[5,49,63,75,99,150],"challenging":[6],"task":[7],"in":[8,19,38,139,180],"text":[9],"classification":[10],"since":[11],"no":[12],"explicit":[13],"cues":[14],"(e.g.,":[15],"swear":[16],"words)":[17],"exist":[18],"the":[20,120,161],"text.":[21],"While":[22],"some":[23],"pre-trained":[24,100,129],"language":[25,101],"models":[26],"have":[27],"been":[28,55],"developed":[29],"for":[30,89,103],"detection,":[33],"they":[34],"are":[35,177],"not":[36,147],"specialized":[37],"implicit":[39,44,104,114,183],"speech.":[41],"Recently,":[42],"an":[43],"dataset":[47],"with":[48,94],"massive":[50],"number":[51],"of":[52,82,124,164,182],"samples":[53,88],"has":[54],"proposed":[56],"by":[57],"controlling":[58],"machine":[59],"generation.":[60],"We":[61,108,159],"propose":[62],"pre-training":[64,93],"approach,":[65],"ConPrompt,":[66,95],"to":[67,127,170],"fully":[68],"leverage":[69],"such":[70],"machine-generated":[71,76],"data.":[72],"Specifically,":[73],"given":[74],"statement,":[77],"we":[78,96,132],"use":[79],"example":[80],"statements":[81],"its":[83,168],"origin":[84],"prompt":[85],"as":[86],"positive":[87],"contrastive":[90],"learning.":[91],"Through":[92],"present":[97],"ToxiGen-ConPrompt,":[98],"model":[102,151],"detection.":[107],"conduct":[109],"extensive":[110],"experiments":[111],"on":[112],"several":[113],"datasets":[117],"and":[118,166,174],"show":[119,134,167],"superior":[121],"generalization":[122],"ability":[123,169],"ToxiGen-ConPrompt":[125,165],"compared":[126],"other":[128],"models.":[130],"Additionally,":[131],"empirically":[133],"that":[135,145],"ConPrompt":[136],"effective":[138],"mitigating":[140],"identity":[141],"term":[142],"bias,":[143],"demonstrating":[144],"it":[146],"only":[148],"makes":[149],"more":[152],"generalizable":[153],"but":[154],"also":[155],"reduces":[156],"unintended":[157],"bias.":[158],"analyze":[160],"representation":[162],"quality":[163],"consider":[171],"target":[172],"group":[173],"toxicity,":[175],"which":[176],"desirable":[178],"features":[179],"terms":[181],"speeches.":[185]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4389520280","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2024-12-07T19:24:43.135013","created_date":"2023-12-11"}