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 …

Although measuring held-out accuracy has been the primary approach to evaluate
generalization, it often overestimates the performance of NLP models, while alternative …

The intelligent manipulation of symbolic knowledge has been a long-sought goal of AI.
However, when it comes to Natural Language Processing (NLP), symbols have to be …

Distributional semantics has deeply changed in the last decades. First, predict models stole
the thunder from traditional count ones, and more recently both of them were replaced in …

An interesting method of evaluating word representations is by how much they reflect the
semantic representations in the human brain. However, most, if not all, previous works only …

Despite an ever-growing number of word representation models introduced for a large
number of languages, there is a lack of a standardized technique to provide insights into …

Sarcasm target detection (identifying the target of mockery in a sarcastic sentence) is an
emerging field in computational linguistics. Although there has been some research in this …

Contextualized embeddings such as BERT and GPT have been shown to give significant
improvement in NLP tasks. On the other hand, static embeddings such as skip-gram and …

How do we design measures of social bias that we trust? While prior work has introduced
several measures, no measure has gained widespread trust: instead, mounting evidence …

Cross-cultural survey research rests upon the assumption that if survey features are kept
constant, data will remain comparable across languages, cultures and countries. Yet …