{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:51:32Z","timestamp":1743040292846,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031333736"},{"type":"electronic","value":"9783031333743"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-33374-3_42","type":"book-chapter","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T10:02:30Z","timestamp":1685095350000},"page":"532-543","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Quantifying the\u00a0Bias of\u00a0Transformer-Based Language Models for\u00a0African American English in\u00a0Masked Language Modeling"],"prefix":"10.1007","author":[{"given":"Flavia","family":"Salutari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jerome","family":"Ramos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hossein A.","family":"Rahmani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonardo","family":"Linguaglossa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aldo","family":"Lipani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,27]]},"reference":[{"key":"42_CR1","doi-asserted-by":"publisher","unstructured":"Basta, C., Costa-juss\u00e0, M.R., Casas, N.: Evaluating the underlying gender bias in contextualized word embeddings. In: Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pp. 33\u201339. Association for Computational Linguistics (Aug 2019). https:\/\/doi.org\/10.18653\/v1\/W19-3805,https:\/\/www.aclweb.org\/anthology\/W19-3805","DOI":"10.18653\/v1\/W19-3805,"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Bender, E.M., Gebru, T., McMillan-Major, A., Shmitchell, S.: On the dangers of stochastic parrots: Can language models be too big? In: ACM Conference on Fairness, Accountability, and Transparency (FAccT) (2021). http:\/\/faculty.washington.edu\/ebender\/papers\/Stochastic_Parrots.pdf","DOI":"10.1145\/3442188.3445922"},{"key":"42_CR3","unstructured":"Bolukbasi, T., Chang, K.W., Zou, J., Saligrama, V., Kalai, A.: Man is to computer programmer as woman is to homemaker? debiasing word embeddings, p. 4356\u20134364. NIPS\u201916, Curran Associates Inc. (2016)"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Cacoullos, R.T., Travis, C.E.: Bilingualism in the Community: Code-switching and Grammars in Contact. Cambridge University Press (2018)","DOI":"10.1017\/9781108235259"},{"key":"42_CR5","doi-asserted-by":"publisher","unstructured":"Chada, R.: Gendered pronoun resolution using BERT and an extractive question answering formulation. In: Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pp. 126\u2013133. Association for Computational Linguistics (Aug 2019). https:\/\/doi.org\/10.18653\/v1\/W19-3819,https:\/\/www.aclweb.org\/anthology\/W19-3819","DOI":"10.18653\/v1\/W19-3819,"},{"key":"42_CR6","unstructured":"Cohen, J.: Statistical Power Analysis for the Behavioral Sciences. Lawrence Erlbaum Associates (1988)"},{"key":"42_CR7","doi-asserted-by":"publisher","unstructured":"Davidson, T., Bhattacharya, D., Weber, I.: Racial bias in hate speech and abusive language detection datasets. In: Proceedings of the Third Workshop on Abusive Language Online, pp. 25\u201335. Association for Computational Linguistics (Aug 2019). https:\/\/doi.org\/10.18653\/v1\/W19-3504,https:\/\/www.aclweb.org\/anthology\/W19-3504","DOI":"10.18653\/v1\/W19-3504,"},{"key":"42_CR8","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (Jun 2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423https:\/\/www.aclweb.org\/anthology\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"42_CR9","unstructured":"Dictionary, C.E.: Cambridge english dictionary (2021), https:\/\/dictionary.cambridge.org\/"},{"key":"42_CR10","doi-asserted-by":"publisher","unstructured":"Dorn, R.: Dialect-specific models for automatic speech recognition of African American Vernacular English. In: Proceedings of the Student Research Workshop Associated with RANLP 2019, pp. 16\u201320. INCOMA Ltd. (Sep 2019). https:\/\/doi.org\/10.26615\/issn.2603-2821.2019_003https:\/\/www.aclweb.org\/anthology\/R19-2003","DOI":"10.26615\/issn.2603-2821.2019_003"},{"key":"42_CR11","unstructured":"Du Bois, J.W., Chafe, W.L., Meyer, C., Thompson, S.A., Martey, N.: Santa barbara corpus of spoken american english (2000). https:\/\/www.linguistics.ucsb.edu\/research\/santa-barbara-corpus\/"},{"key":"42_CR12","unstructured":"Gokaslan, A., Cohen, V.: Openwebtext corpus (2019). http:\/\/web.archive.org\/save\/http:\/\/Skylion007.github.io\/OpenWebTextCorpus"},{"key":"42_CR13","unstructured":"Gorski, P.C.: Reaching and teaching students in poverty: Strategies for erasing the opportunity gap. Teachers College Press (2017)"},{"key":"42_CR14","doi-asserted-by":"publisher","unstructured":"Green, L.J.: Introduction, pp. 1\u201311. Cambridge University Press (2002). https:\/\/doi.org\/10.1017\/CBO9780511800306.005","DOI":"10.1017\/CBO9780511800306.005"},{"key":"42_CR15","doi-asserted-by":"publisher","unstructured":"Green, L.J.: Syntax part 1: verbal markers in AAE, p. 34\u201375. Cambridge University Press (2002). https:\/\/doi.org\/10.1017\/CBO9780511800306.005","DOI":"10.1017\/CBO9780511800306.005"},{"issue":"4","key":"42_CR16","doi-asserted-by":"publisher","first-page":"2135","DOI":"10.1093\/qje\/qjz021","volume":"134","author":"TA Hassan","year":"2019","unstructured":"Hassan, T.A., Hollander, S., van Lent, L., Tahoun, A.: Firm-level political risk: measurement and effects. Q. J. Econ. 134(4), 2135\u20132202 (2019)","journal-title":"Q. J. Econ."},{"key":"42_CR17","unstructured":"Huang, J., et al.: Cross-language transfer learning, continuous learning, and domain adaptation for end-to-end automatic speech recognition. arXiv preprint arXiv:2005.04290 (2020)"},{"key":"42_CR18","doi-asserted-by":"publisher","unstructured":"Hutchinson, B., Prabhakaran, V., Denton, E., Webster, K., Zhong, Y., Denuyl, S.: Social biases in NLP models as barriers for persons with disabilities. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5491\u20135501. Association for Computational Linguistics (Jul 2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.487https:\/\/www.aclweb.org\/anthology\/2020.acl-main.487","DOI":"10.18653\/v1\/2020.acl-main.487"},{"key":"42_CR19","unstructured":"Kendall, T., Farrington, C.: The corpus of regional african american language (2018). http:\/\/lingtools.uoregon.edu\/coraal\/"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Kurita, K., Vyas, N., Pareek, A., Black, A.W., Tsvetkov, Y.: Measuring bias in contextualized word representations. In: Proceedings of the First Workshop on Gender Bias in Natural Language Processing. Association for Computational Linguistics (2019). https:\/\/www.aclweb.org\/anthology\/W19-3823","DOI":"10.18653\/v1\/W19-3823"},{"key":"42_CR21","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: A lite bert for self-supervised learning of language representations. In: Proceedings of the 2020 International Conference on Learning Representations (2020). https:\/\/openreview.net\/pdf?id=H1eA7AEtvS"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871\u20137880. Association for Computational Linguistics (Jul 2020). 10.18653\/v1\/2020.acl-main.703, https:\/\/www.aclweb.org\/anthology\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Liang, P.P., Li, I.M., Zheng, E., Lim, Y.C., Salakhutdinov, R., Morency, L.P.: Towards debiasing sentence representations. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (2020). https:\/\/www.aclweb.org\/anthology\/2020.acl-main.488","DOI":"10.18653\/v1\/2020.acl-main.488"},{"key":"42_CR24","unstructured":"Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"42_CR25","doi-asserted-by":"crossref","unstructured":"Luu, A., Malamud, S.A.: Non-topical coherence in social talk: A call for dialogue model enrichment. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pp. 118\u2013133 (2020)","DOI":"10.18653\/v1\/2020.acl-srw.17"},{"key":"42_CR26","doi-asserted-by":"publisher","unstructured":"May, C., Wang, A., Bordia, S., Bowman, S.R., Rudinger, R.: On measuring social biases in sentence encoders. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 622\u2013628. Association for Computational Linguistics (Jun 2019). https:\/\/doi.org\/10.18653\/v1\/N19-1063https:\/\/www.aclweb.org\/anthology\/N19-1063","DOI":"10.18653\/v1\/N19-1063"},{"key":"42_CR27","unstructured":"Mubarak, H., Rashed, A., Darwish, K., Samih, Y., Abdelali, A.: Arabic offensive language on twitter: Analysis and experiments (2020)"},{"key":"42_CR28","unstructured":"Pullum, G.K.: African american vernacular english is not standard english with mistakes. The workings of language: From prescriptions to perspectives, pp. 59\u201366 (1999)"},{"key":"42_CR29","unstructured":"QuickFacts, U.C.B.: United States census, QuickFacts statistics on U.S. population origin (2019). https:\/\/www.census.gov\/quickfacts\/fact\/table\/US\/PST045219"},{"issue":"8","key":"42_CR30","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"42_CR31","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. In: NeurIPS Energy Efficient Machine Learning and Cognitive Computing Workshop (2019)"},{"key":"42_CR32","doi-asserted-by":"publisher","unstructured":"Shah, D.S., Schwartz, H.A., Hovy, D.: Predictive biases in natural language processing models: A conceptual framework and overview. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. pp. 5248\u20135264. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.468https:\/\/www.aclweb.org\/anthology\/2020.acl-main.468","DOI":"10.18653\/v1\/2020.acl-main.468"},{"key":"42_CR33","doi-asserted-by":"publisher","unstructured":"Sheng, E., Chang, K.W., Natarajan, P., Peng, N.: The woman worked as a babysitter: On biases in language generation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3407\u20133412. Association for Computational Linguistics (Nov 2019). https:\/\/doi.org\/10.18653\/v1\/D19-1339https:\/\/www.aclweb.org\/anthology\/D19-1339","DOI":"10.18653\/v1\/D19-1339"},{"key":"42_CR34","doi-asserted-by":"crossref","unstructured":"Utama, P.A., Moosavi, N.S., Gurevych, I.: Mind the trade-off: Debiasing nlu models without degrading the in-distribution performance (2020)","DOI":"10.18653\/v1\/2020.acl-main.770"},{"issue":"1\/2","key":"42_CR35","doi-asserted-by":"publisher","first-page":"28","DOI":"10.2307\/2332510","volume":"34","author":"BL Welch","year":"1947","unstructured":"Welch, B.L.: The generalization ofstudent\u2019s\u2019 problem when several different population variances are involved. Biometrika 34(1\/2), 28\u201335 (1947)","journal-title":"Biometrika"},{"key":"42_CR36","unstructured":"Wheeler, R., Thomas, J.: And \"still\" the children suffer: The dilemma of standard english, social justice, and social access. In: JAC, pp. 363\u2013396 (2013)"},{"key":"42_CR37","doi-asserted-by":"crossref","unstructured":"Xu, C., Zhou, W., Ge, T., Wei, F., Zhou, M.: BERT-of-theseus: Compressing BERT by progressive module replacing, pp. 7859\u20137869 (Nov 2020). https:\/\/www.aclweb.org\/anthology\/2020.emnlp-main.633","DOI":"10.18653\/v1\/2020.emnlp-main.633"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33374-3_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T20:05:49Z","timestamp":1710360349000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33374-3_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031333736","9783031333743"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33374-3_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Osaka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"813","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"143","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}