The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …

Despite their success, deep networks are used as black-box models with outputs that are not
easily explainable during the learning and the prediction phases. This lack of interpretability …

State-of-the-art models in NLP are now predominantly based on deep neural networks that
are opaque in terms of how they come to make predictions. This limitation has increased …

Transformer architectures have proven to learn useful representations for protein
classification and generation tasks. However, these representations present challenges in …

Graph neural networks (GNNs) have become a popular approach to integrating structural
inductive biases into NLP models. However, there has been little work on interpreting them …

We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

There is a recent surge of interest in using attention as explanation of model predictions,
with mixed evidence on whether attention can be used as such. While attention conveniently …

Feature attribution methods are popular in interpretable machine learning. These methods
compute the attribution of each input feature to represent its importance, but there is no …

Transformer models have demonstrated their promising potential and achieved excellent
performance on a series of computer vision tasks. However, the huge computational cost of …

Selective rationalization improves neural network interpretability by identifying a small
subset of input features {—} the rationale {—} that best explains or supports the prediction. A …