This paper provides an entry point to the problem of interpreting a deep neural network
model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. As a …

Neural networks for NLP are becoming increasingly complex and widespread, and there is a
growing concern if these models are responsible to use. Explaining models helps to address …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Large language models (LLMs) have demonstrated impressive capabilities in natural
language processing. However, their internal mechanisms are still unclear and this lack of …

Current learning machines have successfully solved hard application problems, reaching
high accuracy and displaying seemingly intelligent behavior. Here we apply recent …

In the last decade, with availability of large datasets and more computing power, machine
learning systems have achieved (super) human performance in a wide variety of tasks …

Recent years have seen important advances in the quality of state-of-the-art models, but this
has come at the expense of models becoming less interpretable. This survey presents an …

Attention mechanisms have recently boosted performance on a range of NLP tasks.
Because attention layers explicitly weight input components' representations, it is also often …

We address the problem of adversarial attacks on text classification, which is rarely studied
comparing to attacks on image classification. The challenge of this task is to generate …

Contextual word representations derived from large-scale neural language models are
successful across a diverse set of NLP tasks, suggesting that they encode useful and …