Reproducibility Report: Contextualizing Hate Speech Classifiers with Post-hoc Explanation
It addresses reproducibility in ML research, which is crucial for researchers and practitioners to validate findings, but is incremental as it replicates existing work.
This report evaluates a prior paper on hate speech classifiers with post-hoc explanations, focusing on reproducing the method and verifying the stated results through experiments and evaluations.
The presented report evaluates Contextualizing Hate Speech Classifiers with Post-hoc Explanation paper within the scope of ML Reproducibility Challenge 2020. Our work focuses on both aspects constituting the paper: the method itself and the validity of the stated results. In the following sections, we have described the paper, related works, algorithmic frameworks, our experiments and evaluations.