{"type":"ScholarlyArticle","title":"From Pink and Blue to a Rainbow Hue! Defying Gender Bias through Gender Neutralizing Text Transformations","authors":[{"name":"Gopendra Vikram Singh","slug":"gopendra-vikram-singh","given":"Gopendra Vikram","family":"Singh","affiliation":"Department of Computer Science and Engineering , Indian Institute of Technology Patna , Patna , India"},{"name":"Soumitra Ghosh","slug":"soumitra-ghosh","given":"Soumitra","family":"Ghosh","affiliation":"NLP Research Group , Fondazione Bruno Kessler (FBK) , Trento , Italy"},{"name":"Neil Dcruze","slug":"neil-dcruze","given":"Neil","family":"Dcruze","affiliation":"Middlebury College , Middlebury , Vermont , United States"},{"name":"Asif Ekbal","slug":"asif-ekbal","given":"Asif","family":"Ekbal","affiliation":"School of AI and Data Science , IIT Jodhpur"}],"abstract":"In an era where language biases contribute to societal inequalities, this research focuses on gender bias in textual data, with profound implications for promoting inclusivity and equity, aligning with United Nations Sustainable Development Goals (SDGs) and upholding the principle of Leave No One Behind (LNOB). Leveraging advances in artificial intelligence, the study introduces the GEnder-NEutralizing Text Transformation (GENETT) framework, addressing gender bias in text through auto-encoders, vector quantization, and Neutrality-Infused Stylization. Furthermore, we present the first-of-its-kind corpus of GEnder Neutralized REvisions (GENRE) crafted from gender-stereotyped versions. This corpus serves a multifaceted utility, offering a resource for diverse downstream tasks in gender-bias analysis. Extensive experimentation on GENRE highlights the superiority of the proposed model over established baselines and state-of-the-art methods. Access the code and dataset at 1. https://www.iitp.ac.in/~ai-nlp-ml/resources.html#GNR, 2. https://github.com/Soumitra816/GNR.\r\n\r\nNote: Our research focuses on understanding cyber harassment conversations, especially in under-researched areas, with the exclusion of non-binary cases due to existing dataset limitations, not lack of sensitivity. We strive for inclusivity and plan to address this in future research with suitable datasets.","doi":"10.24963/ijcai.2024/824","url":"https://ijcai.org/proceedings/2024/824","pdf":"https://ijcai.org/proceedings/2024/0824.pdf","markdown":"https://ijcai.org/proceedings/2024/824.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/824","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI for Good","track":"AI for Good","number":824,"pages":{"first":7447,"last":7455},"keywords":["AI Ethics, Trust, Fairness: General","Multidisciplinary Topics and Applications: General"],"videos":[],"references":[{"position":1,"raw":"[Badaloni and Rodà, 2022] Silvana Badaloni and Antonio Rodà. Gender knowledge and artificial intelligence (short paper). In Guido Boella, Fabio Aurelio D'Asaro, Abeer Dyoub, and Giuseppe Primiero, editors, Proceedings of 1st Workshop on Bias, Ethical AI, Explainability and the Role of Logic and Logic Programming (BEWARE 2022) co-located with the 21th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2022), Udine, Italy, December 2, 2022, volume 3319 of CEUR Workshop Proceedings, pages 107-112. CEUR-WS.org, 2022.","title":"Silvana Badaloni and Antonio Rodà. Gender knowledge and artificial intelligence (short paper)","authors":"Rodà Badaloni","year":"2022","venue":"Proceedings of 1st Workshop on Bias, Ethical AI, Explainability and the Role of Logic and Logic Programming (BEWARE 2022) co-located with the 21th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2022)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chiril et al., 2020] Patricia Chiril, Véronique Moriceau, Farah Benamara, Alda Mari, Gloria Origgi, and Marlène Coulomb-Gully. He said \"who's gonna take care of your children when you are at acl?\": Reported sexist acts are not sexist. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pages 4055-4066. As- sociation for Computational Linguistics, 2020.","title":"He said \"who's gonna take care of your children when you are at acl?\": Reported sexist acts are not sexist","authors":"Patricia Chiril, Véronique Moriceau, Farah Benamara, Alda Mari, Gloria Origgi, Marlène Coulomb-Gully","year":"2020","venue":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cohen et al., 2023] Alma Cohen, Tzur Karelitz, Tamar Kricheli-Katz, Sephi Pumpian, and Tali Regev. Gender- neutral language and gender disparities. NBER Working Paper, (w31400), 2023.","title":"Genderneutral language and gender disparities","authors":"Alma Cohen, Tzur Karelitz, Tamar Kricheli-Katz, Sephi Pumpian, Tali Regev","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fersini et al., 2018] Elisabetta Fersini, Paolo Rosso, and Maria Anzovino. Overview of the task on automatic misogyny identification at ibereval 2018. Ibereval@ se- pln, 2150:214-228, 2018.","title":"Overview of the task on automatic misogyny identification at ibereval 2018","authors":"Elisabetta Fersini, Paolo Rosso, Maria Anzovino","year":"2018","venue":"Ibereval@ sepln","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fu et al., 2018] Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. Style transfer in text: Ex- ploration and evaluation. In Sheila A. McIlraith and Kil- ian Q. Weinberger, editors, Proceedings of the Thirty- Second AAAI Conference on Artificial Intelligence, (AAAI- 18), the 30th innovative Applications of Artificial Intelli- gence (IAAI-18), and the 8th AAAI Symposium on Educa- tional Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, pages 663- 670. AAAI Press, 2018.","title":"Style transfer in text: Exploration and evaluation","authors":"Fu","year":"2018","venue":"AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Garimella et al., 2021] Aparna Garimella, Akhash Amar- nath, Kiran Kumar, Akash Pramod Yalla, Anandhavelu Natarajan, Niyati Chhaya, and Balaji Vasan Srinivasan. He is very intelligent, she is very beautiful? on mitigat- ing social biases in language modelling and generation. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Nav- igli, editors, Findings of the Association for Computa- tional Linguistics: ACL/IJCNLP 2021, Online Event, Au- gust 1-6, 2021, volume ACL/IJCNLP 2021 of Findings of ACL, pages 4534-4545. Association for Computational Linguistics, 2021.","title":"He is very intelligent, she is very beautiful? on mitigating social biases in language modelling and generation","authors":"Aparna Garimella, Akhash Amarnath, Kiran Kumar, Akash Pramod Yalla, Anandhavelu Natarajan, Niyati Chhaya, Balaji Vasan Srinivasan","year":"2021","venue":"Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Grosz and Conde-Cespedes, 2020] Dylan Grosz and Patri- cia Conde-Cespedes. Automatic detection of sexist state- ments commonly used at the workplace. In Trends and Applications in Knowledge Discovery and Data Mining: PAKDD 2020 Workshops, DSFN, GII, BDM, LDRC and LBD, Singapore, May 11-14, 2020, Revised Selected Pa- pers 24, pages 104-115. Springer, 2020.","title":"Dylan Grosz and Patricia Conde-Cespedes. Automatic detection of sexist statements commonly used at the workplace","authors":"Conde-Cespedes Grosz","year":"2020","venue":"Trends and Applications in Knowledge Discovery and Data Mining: PAKDD 2020 Workshops, DSFN, GII, BDM, LDRC and LBD","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2021] Junxian He, Xinyi Wang, Graham Neubig, and Taylor Berg-Kirkpatrick. A probabilistic formula- tion of unsupervised text style transfer. arXiv preprint arXiv:2002.03912, 2021.","title":"A probabilistic formulation of unsupervised text style transfer","authors":"He","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hu et al., 2017] Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. Toward controlled generation of text. In International conference on machine learning, pages 1587-1596. PMLR, 2017.","title":"Toward controlled generation of text","authors":"Hu","year":"2017","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hu et al., 2022] Shenggang Hu, Jabir Alshehabi Al-Ani, Karen D. Hughes, Nicole Denier, Alla Konnikov, Lei Ding, Jinhan Xie, Yang Hu, Monideepa Tarafdar, Bei Jiang, Linglong Kong, and Hongsheng Dai. Balancing gender bias in job advertisements with text-level bias mit- igation. Frontiers Big Data, 5:805713, 2022.","title":"Balancing gender bias in job advertisements with text-level bias mitigation","authors":"Hu","year":"2022","venue":"Frontiers Big Data","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[John et al., 2018] Vineet John, Lili Mou, Hareesh Bahu- leyan, and Olga Vechtomova. Disentangled representation learning for non-parallel text style transfer. arXiv preprint arXiv:1808.04339, 2018.","title":"Disentangled representation learning for non-parallel text style transfer","authors":"Vineet John, Lili Mou, Hareesh Bahuleyan, Olga Vechtomova","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In 3rd Inter- national Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"3rd International Conference on Learning Representations, ICLR 2015","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lewis et al., 2019] Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. Bart: De- noising sequence-to-sequence pre-training for natural lan- guage generation, translation, and comprehension. arXiv preprint arXiv:1910.13461, 2019.","title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","authors":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, Luke Zettlemoyer","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Luo et al., 2019] Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Zhifang Sui, and Xu Sun. A dual reinforcement learning framework for unsupervised text style transfer. arXiv preprint arXiv:1905.10060, 2019.","title":"A dual reinforcement learning framework for unsupervised text style transfer","authors":"Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Zhifang Sui, Xu Sun","year":"2019","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2019/711"},{"position":15,"raw":"[Piergentili et al., 2023] Andrea Piergentili, Dennis Fucci, Beatrice Savoldi, Luisa Bentivogli, and Matteo Negri. From inclusive language to gender-neutral machine trans- lation. arXiv preprint arXiv:2301.10075, 2023.","title":"From inclusive language to gender-neutral machine translation","authors":"Andrea Piergentili, Dennis Fucci, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Prabhumoye et al., 2018] Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, and Alan W Black. Style transfer through back-translation. arXiv preprint arXiv:1804.09000, 2018.","title":"Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, and Alan W Black. Style transfer through back-translation","authors":"Prabhumoye","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rodríguez-Sánchez et al., 2021] Francisco Rodríguez- Sánchez, Jorge Carrillo-de Albornoz, Laura Plaza, Julio Gonzalo, Paolo Rosso, Miriam Comet, and Trinidad Donoso. Overview of exist 2021: sexism identification in social networks. Procesamiento del Lenguaje Natural, 67:195-207, 2021.","title":"Overview of exist 2021: sexism identification in social networks","authors":"Rodríguez-Sánchez","year":"2021","venue":"Procesamiento del Lenguaje Natural","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Samory et al., 2021] Mattia Samory, Indira Sen, Julian Kohne, Fabian Flöck, and Claudia Wagner. \"call me sex- ist, but...\": Revisiting sexism detection using psychologi- cal scales and adversarial samples. In Proceedings of the International AAAI Conference on Web and Social Media, volume 15, pages 573-584, 2021.","title":"Revisiting sexism detection using psychological scales and adversarial samples","authors":"Mattia Samory, Indira Sen, Julian Kohne, Fabian Flöck, Claudia Wagner","year":"2021","venue":"Proceedings of the International AAAI Conference on Web and Social Media","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shen et al., 2017] Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. Style transfer from non-parallel text by cross-alignment. Advances in neural information pro- cessing systems, 30, 2017.","title":"Style transfer from non-parallel text by cross-alignment","authors":"Shen","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Singh et al., 2022] Gopendra Vikram Singh, Mauajama Fir- daus, Shruti Mishra, Asif Ekbal, et al. Knowing what to say: Towards knowledge grounded code-mixed response generation for open-domain conversations. Knowledge- Based Systems, 249:108900, 2022.","title":"Knowing what to say: Towards knowledge grounded code-mixed response generation for open-domain conversations","authors":"Singh","year":"2022","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Singh et al., 2023] Gopendra Singh, Soumitra Ghosh, and Asif Ekbal. Promoting gender equality through gender- biased language analysis in social media. In Proceedings of the Thirty-Second International Joint Conference on Ar- tificial Intelligence, pages 6210-6218, 2023.","title":"Promoting gender equality through genderbiased language analysis in social media","authors":"Singh","year":"2023","venue":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Waseem and Hovy, 2016] Zeerak Waseem and Dirk Hovy. Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In Proceedings of the NAACL student research workshop, pages 88-93, 2016.","title":"Hateful symbols or hateful people? predictive features for hate speech detection on twitter","authors":"Hovy Waseem, Zeerak Waseem, Dirk Hovy","year":"2016","venue":"Proceedings of the NAACL student research workshop","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2019] Chen Wu, Xuancheng Ren, Fuli Luo, and Xu Sun. A hierarchical reinforced sequence operation method for unsupervised text style transfer. arXiv preprint arXiv:1906.01833, 2019.","title":"A hierarchical reinforced sequence operation method for unsupervised text style transfer","authors":"Chen Wu, Xuancheng Ren, Fuli Luo, Xu Sun","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang and Feng, 2020] Zekun Yang and Juan Feng. A causal inference method for reducing gender bias in word em- bedding relations. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Confer- ence, IAAI 2020, The Tenth AAAI Symposium on Educa- tional Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pages 9434-9441. AAAI Press, 2020.","title":"A causal inference method for reducing gender bias in word embedding relations","authors":"Yang, Feng ; ] Zekun Yang, Juan Feng","year":"2020","venue":"The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhao et al., 2018a] Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. Gender bias in coreference resolution: Evaluation and debiasing methods. In Marilyn A. Walker, Heng Ji, and Amanda Stent, editors, Proceedings of the 2018 Conference of the North Ameri- can Chapter of the Association for Computational Linguis- tics: Human Language Technologies, NAACL-HLT, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 2 (Short Papers), pages 15-20. Association for Computational Lin- guistics, 2018.","title":"Gender bias in coreference resolution: Evaluation and debiasing methods","authors":"Zhao","year":"2018","venue":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhao et al., 2018b] Junbo Zhao, Yoon Kim, Kelly Zhang, Alexander Rush, and Yann LeCun. Adversarially regular- ized autoencoders. In International conference on machine learning, pages 5902-5911. PMLR, 2018.","title":"Adversarially regularized autoencoders","authors":"Zhao","year":"2018","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhao et al., 2019] Jieyu Zhao, Tianlu Wang, Mark Yatskar, Ryan Cotterell, Vicente Ordonez, and Kai-Wei Chang. Gender bias in contextualized word embeddings. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Pro- ceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Min- neapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pages 629-634. Association for Computa- tional Linguistics, 2019.","title":"Gender bias in contextualized word embeddings","authors":"Zhao","year":"2019","venue":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhou et al., 2019] Pei Zhou, Weijia Shi, Jieyu Zhao, Kuan- Hao Huang, Muhao Chen, and Kai-Wei Chang. Analyzing and mitigating gender bias in languages with grammatical gender and bilingual word embeddings. ACL: Montréal, QC, Canada, 2019.","title":"Analyzing and mitigating gender bias in languages with grammatical gender and bilingual word embeddings","authors":"Pei Zhou, Weijia Shi, Jieyu Zhao, Kuan-Hao Huang, Muhao Chen, Kai-Wei Chang","year":"2019","venue":"ACL: Montréal","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}