Machine learning has been heavily researched and widely used in many disciplines.
However, achieving high accuracy requires a large amount of data that is sometimes …

Background The large and growing number of published studies, and their increasing rate of
publication, makes the task of identifying relevant studies in an unbiased way for inclusion in …

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 …

Deep neural networks have demonstrated excellent performances in many real-world
applications. Unfortunately, they may show Clever Hans-like behaviour (making use of …

Although interactive learning puts the user into the loop, the learner remains mostly a black
box for the user. Understanding the reasons behind predictions and queries is important …

In many settings it is important for one to be able to understand why a model made a
particular prediction. In NLP this often entails extracting snippets of an input textresponsible …

Medical researchers looking for evidence pertinent to a specific clinical question must
navigate an increasingly voluminous corpus of published literature. This data deluge has …

Explanations have gained an increasing level of interest in the AI and Machine Learning
(ML) communities in order to improve model transparency and allow users to form a mental …

We present a new Convolutional Neural Network (CNN) model for text classification that
jointly exploits labels on documents and their constituent sentences. Specifically, we …

Many methods now exist for conditioning model outputs on task instructions, retrieved
documents, and user-provided explanations and feedback. Rather than relying solely on …