no code implementations • 6 Mar 2023 • Peyman Jalali, Nengfeng Zhou, Yufei Yu
Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons.
no code implementations • 14 Jun 2021 • Shafie Gholizadeh, Nengfeng Zhou
We then applied one of the NLP explainability methods Layer-wise Relevance Propagation (LRP) to a NLP classification model.
no code implementations • 13 May 2021 • Nengfeng Zhou, Zach Zhang, Vijayan N. Nair, Harsh Singhal, Jie Chen, Agus Sudjianto
In this paper, we provide an overview of bias and fairness issues that arise with the use of ML algorithms.
no code implementations • 6 Apr 2021 • Lian Yu, Nengfeng Zhou
Imbalanced data set is a problem often found and well-studied in financial industry.