LIME

AbstractInterpretability of machine learning (ML) models becomes more relevant with their increasing adoption. In this work, we address the interpretability of ML based question answering (QA) models on a combination …...

AbstractIn this paper, we focus on quantifying model stability as a function of random seed by investigating the effects of the induced randomness on model performance and the robustness of …...

AbstractNeural network NLP models are vulnerable to small modifications of the input that maintain the original meaning but result in a different prediction. In this paper, we focus on robustness …...

AbstractAlgorithmic approaches to interpreting machine learning models have proliferated in recent years. We carry out human subject tests that are the first of their kind to isolate the effect of …...

AbstractThis paper presents our system submission to task 5: Toxic Spans Detection of the SemEval-2021 competition. The competition aims at detecting the spans that make a toxic span toxic. In …...

AbstractLifelong Learning (LL) black-box models are dynamic in that they keep learning from new tasks and constantly update their parameters. Owing to the need to utilize information from previously seen …...

AbstractToxic spans detection is an emerging challenge that aims to find toxic spans within a toxic text. In this paper, we describe our solutions to tackle toxic spans detection. The …...

AbstractEmotion detection can provide us with a window into understanding human behavior. Due to the complex dynamics of human emotions, however, constructing annotated datasets to train automated models can be …...

AbstractA principle behind dozens of attribution methods is to take the prediction difference between before-and-after an input feature (here, a token) is removed as its attribution. A popular Input Marginalization …...

AbstractRecently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have only been applied to vision and tabular data, …...