Publications

  • W. Wu, D. Arendt, S. Volkova. (2021) Evaluating Neural Machine Comprehension Model Robustness to Noisy Inputs and Adversarial Attacks. EACL’21.
  • Arendt, D., Huang, Z., Shrestha, P., Ayton, E., Glenski, M., & Volkova, S. (2021). CrossCheck: Rapid, Reproducible, and Interpretable Model Evaluation. Workshop on Data Science with Human-in-the-loop: Language Advances (DaSH-LA) collocated with NAACL 2021 
  • Arendt, D. L. (2020). Parallel embeddings: a visualization technique for contrasting learned representations. Proceedings of the 25th International Conference on Intelligent User Interfaces. 
  • M. Glenski, E. Ayton, R. Cosbey, D. Arendt, and S. Volkova. (2020). Towards Trustworthy Deception Detection: Benchmarking Model Robustness across Domains, Modalities, and Languages. International Workshop on Rumors and Deception in Social Media at COLING.
  • M. Glenski, E. Ayton, R. Cosbey, D. Arendt, and S. Volkova. (2021). Evaluating Deception Detection Model Robustness to Linguistic Variation." In International Workshop on Natural Language Processing for Social Media (SocialNLP)
  • E. Saldanha, R. Cosbey, E. Ayton, M. Glenski, J. Cottam, K. Shivaram, B. Jefferson, B. Hutchinson, D. Arendt, S. Volkova. (2020) Evaluation of Algorithm Selection and Ensemble Methods for Causal Discovery. NeurIPS Workshop on Causal Discovery and Causality-Inspired Machine Learning.
  • E. Saldanha, L. M. Blaha, A. V. Sathanur, N. Hodas, S. Volkova, and M. Greaves. (2019). Evaluation and Validation Approaches for Simulation of Social Behavior: Challenges and Opportunities. In Social-Behavioral Modeling for Complex Systems.
  • Volkova, S., Ayton, E., Arendt, D., Huang, Z., and Hutchinson, B. (2019). Explaining Multimodal Deceptive News Prediction Models. Proceedings of the International AAAI Conference on Web and Social Media.
  • Saldanha, E., Praggastis, B., Billow, T., and Arendt, D. (2019). ReLVis: Visual Analytics for Situational Awareness During Reinforcement Learning Experimentation. EuroVis.
  • Arendt, D., E. Grace, and S. Volkova. (2018). Interactive machine learning at scale with CHISSL. In Thirty-Second AAAI Conference on Artificial Intelligence.
  • Arendt, D., and Volkova, S. (2017). ESTEEM: A novel framework for qualitatively evaluating and visualizing spatiotemporal embeddings in social media. Proceedings of ACL 2017, System Demonstrations. 
  • Cottam J.A., M.F. Glenski, Z.H. Shaw, R.S. Rabello, A.J. Golding, S. Volkova, and D.L. Arendt. 2021. "Graph Comparison for Causal Discovery." In Visualization in Data Science 2021.
  • Yang F., Z. Huang, J. Scholtz, and D.L. Arendt. "How do visual explanations foster end users' appropriate trust in machine learning?" Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • Duskin K.R., S. Sharma, J. Yun, E.G. Saldanha, and D.L. Arendt. 2021. "Evaluating and Explaining Natural Language Generation with GenX." In 2nd Workshop on Data Science with Human-in-the-loop: Language Advances. 
  • Arendt, Dustin, and Zhuanyi Huang. "Machine Learning Model Explanation Apparatus and Methods." U.S. Patent Application No. 16/555,530.