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) …

End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to
understand. This has given rise to numerous efforts towards model explainability in recent …

In interpretable NLP, we require faithful rationales that reflect the model's decision-making
process for an explained instance. While prior work focuses on extractive rationales (a …

Large language models (LLMs) are trained to imitate humans to explain human decisions.
However, do LLMs explain themselves? Can they help humans build mental models of how …

Saliency methods are widely used to interpret neural network predictions, but different
variants of saliency methods often disagree even on the interpretations of the same …

Winograd schemas are a well-established tool for evaluating coreference resolution (CoR)
and commonsense reasoning (CSR) capabilities of computational models. So far, schemas …

Automatic machine translation is super efficient to produce translations yet their quality is not
guaranteed. This technique report introduces TranSmart, a practical human-machine …

For the longest time, translation was a labor-intensive process that required just human
effort. While human translation remains the most reliable method of textual content …

While the attention heatmaps produced by neural machine translation (NMT) models seem
insightful, there is little evidence that they reflect a model's true internal reasoning. We …

Despite the prominence of neural abstractive summarization models, we know little about
how they actually form summaries and how to understand where their decisions come from …