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) …

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 …

A key goal for cognitive neuroscience is to understand the neurocognitive systems that
support semantic memory. Recent multivariate analyses of neuroimaging data have …

Neural network models have achieved state-of-the-art performances in a wide range of
natural language processing (NLP) tasks. However, a long-standing criticism against neural …

Abstract Language models (LMs) automatically learn word embeddings during pre-training
on language corpora. Although word embeddings are usually interpreted as feature vectors …

A central goal in the cognitive sciences is the development of numerical models for mental
representations of object concepts. This paper introduces Variational Interpretable Concept …

We propose bidirectional imparting or BiImp, a generalized method for aligning embedding
dimensions with concepts during the embedding learning phase. While preserving the …

In recent years, large language models (LMs) have achieved remarkable progress across
various natural language processing tasks. As pre-training and fine-tuning are costly and …

Polysemy is an inherent characteristic of natural language. In order to make it easier to
distinguish between different senses of polysemous words, we propose a method for …

Texts are the major information carrier for internet users, from which learning the latent
representations has important research and practical value. Neural topic models have been …