Despite the rising popularity of saliency-based explanations, the resear...
Recent progress in generative models has resulted in models that produce...
In recent years, NLP practitioners have converged on the following pract...
Many adversarial attacks in NLP perturb inputs to produce visually simil...
Many practical applications, ranging from paper-reviewer assignment in p...
Neural networks are known to exploit spurious artifacts (or shortcuts) t...
Modern machine learning models are opaque, and as a result there is a
bu...
In attempts to "explain" predictions of machine learning models, researc...
While many methods purport to explain predictions by highlighting salien...
For many prediction tasks, stakeholders desire not only predictions but ...
We introduce NeuSpell, an open-source toolkit for spelling correction in...
Pooling-based recurrent neural architectures consistently outperform the...
Attention mechanisms are ubiquitous components in neural architectures
a...
To combat adversarial spelling mistakes, we propose placing a word
recog...
In this paper, we describe compare-mt, a tool for holistic analysis and
...
Recent success of deep learning models for the task of extractive Questi...
Prediction without justification has limited utility. Much of the succes...