Analyzing the Limits of Self-Supervision in Handling Bias in Language
暂无分享,去创建一个
Dilek Z. Hakkani-Tür | Mohit Bansal | Spandana Gella | Yang Liu | Karthik Gopalakrishnan | Lisa Bauer
[1] Yoav Goldberg,et al. Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space , 2022, EMNLP.
[2] M. Shoeybi,et al. Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models , 2022, NeurIPS.
[3] Hua Wu,et al. PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation , 2021, AACL/IJCNLP.
[4] Goran Glavas,et al. Sustainable Modular Debiasing of Language Models , 2021, EMNLP.
[5] Ellie Pavlick,et al. Do Prompt-Based Models Really Understand the Meaning of Their Prompts? , 2021, NAACL.
[6] Michael S. Bernstein,et al. On the Opportunities and Risks of Foundation Models , 2021, ArXiv.
[7] Philipp Koehn,et al. Facebook AI’s WMT21 News Translation Task Submission , 2021, WMT.
[8] Hiroaki Hayashi,et al. Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing , 2021, ACM Comput. Surv..
[9] Ruslan Salakhutdinov,et al. Towards Understanding and Mitigating Social Biases in Language Models , 2021, ICML.
[10] Dong Nguyen,et al. Introducing CAD: the Contextual Abuse Dataset , 2021, NAACL.
[11] Yejin Choi,et al. DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts , 2021, ACL.
[12] Brian Lester,et al. The Power of Scale for Parameter-Efficient Prompt Tuning , 2021, EMNLP.
[13] Olatunji Ruwase,et al. ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep learning , 2021, SC21: International Conference for High Performance Computing, Networking, Storage and Analysis.
[14] Timo Schick,et al. Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP , 2021, Transactions of the Association for Computational Linguistics.
[15] Charles Foster,et al. The Pile: An 800GB Dataset of Diverse Text for Language Modeling , 2020, ArXiv.
[16] Matt Gardner,et al. Learning from Task Descriptions , 2020, EMNLP.
[17] Yejin Choi,et al. PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction , 2020, EMNLP.
[18] Omer Levy,et al. The Turking Test: Can Language Models Understand Instructions? , 2020, ArXiv.
[19] Samuel R. Bowman,et al. CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models , 2020, EMNLP.
[20] Yejin Choi,et al. RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models , 2020, FINDINGS.
[21] Hinrich Schütze,et al. It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners , 2020, NAACL.
[22] Armen Aghajanyan,et al. Pre-training via Paraphrasing , 2020, NeurIPS.
[23] Mark Chen,et al. Language Models are Few-Shot Learners , 2020, NeurIPS.
[24] R. Socher,et al. A Simple Language Model for Task-Oriented Dialogue , 2020, NeurIPS.
[25] Siva Reddy,et al. StereoSet: Measuring stereotypical bias in pretrained language models , 2020, ACL.
[26] Timo Schick,et al. Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference , 2020, EACL.
[27] Noah A. Smith,et al. Social Bias Frames: Reasoning about Social and Power Implications of Language , 2019, ACL.
[28] Colin Raffel,et al. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer , 2019, J. Mach. Learn. Res..
[29] Samyam Rajbhandari,et al. ZeRO: Memory optimizations Toward Training Trillion Parameter Models , 2019, SC20: International Conference for High Performance Computing, Networking, Storage and Analysis.
[30] M. Shoeybi,et al. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism , 2019, ArXiv.
[31] Nanyun Peng,et al. The Woman Worked as a Babysitter: On Biases in Language Generation , 2019, EMNLP.
[32] Ankur Bapna,et al. Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges , 2019, ArXiv.
[33] D. Hillson. What Are Opportunities? , 2019, Capturing Upside Risk.
[34] Yejin Choi,et al. The Curious Case of Neural Text Degeneration , 2019, ICLR.
[35] Lucy Vasserman,et al. Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification , 2019, WWW.
[36] Mona Attariyan,et al. Parameter-Efficient Transfer Learning for NLP , 2019, ICML.
[37] Lukasz Kaiser,et al. Attention is All you Need , 2017, NIPS.
[38] Andrea Vedaldi,et al. Learning multiple visual domains with residual adapters , 2017, NIPS.
[39] Ian S. Dunn,et al. Exploring the Limits , 2009 .
[40] Yi Yang,et al. Auto-Debias: Debiasing Masked Language Models with Automated Biased Prompts , 2022, ACL.
[41] Nanyun Peng,et al. What do Bias Measures Measure? , 2021, ArXiv.
[42] Ilya Sutskever,et al. Language Models are Unsupervised Multitask Learners , 2019 .