Related papers: Visualizing Attention in Transformer-Based Languag…

The self-attention module is a key component of Transformer-based models, wherein each token pays attention to every other token. Recent studies have shown that these heads exhibit syntactic, semantic, or local behaviour. Some studies have…

Object-based attention is a key component of the visual system, relevant for perception, learning, and memory. Neurons tuned to features of attended objects tend to be more active than those associated with non-attended objects. There is a…

Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BERT, XLNet, etc.) based on Transformer (Vaswani et al. 2017), and in a range of end tasks, such models have achieved state-of-the-art…

Self-attention in vision transformers is often thought to perform perceptual grouping where tokens attend to other tokens with similar embeddings, which could correspond to semantically similar features of an object. However, attending to…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Transformer-based language models significantly advanced the state-of-the-art in many linguistic tasks. As this revolution continues, the ability to explain model predictions has become a major area of interest for the NLP community. In…

Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest. Existing models typically rely on top-down language information and learn attention implicitly…

This paper presents the first comprehensive interpretability analysis of a Transformer-based Sign Language Translation (SLT) model, focusing on the translation from video-based Greek Sign Language to glosses and text. Leveraging the Greek…

Image captioning involves generating textual descriptions from input images, bridging the gap between computer vision and natural language processing. Recent advancements in transformer-based models have significantly improved caption…

We introduce "talking-heads attention" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of…

Developing neural architectures that are capable of logical reasoning has become increasingly important for a wide range of applications (e.g., natural language processing). Towards this grand objective, we propose a symbolic reasoning…

Recent work in computational psycholinguistics has revealed intriguing parallels between attention mechanisms and human memory retrieval, focusing primarily on vanilla Transformers that operate on token-level representations. However,…

Recent research has explored the memorization capacity of multi-head attention, but these findings are constrained by unrealistic limitations on the context size. We present a novel proof for language-based Transformers that extends the…

In this paper, we seek solutions for reducing the computation complexity of transformer-based models for speech representation learning. We evaluate 10 attention algorithms; then, we pre-train the transformer-based model with those…

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

Attention level estimation systems have a high potential in many use cases, such as human-robot interaction, driver modeling and smart home systems, since being able to measure a person's attention level opens the possibility to natural…

Transformer-based models, even though achieving super-human performance on several downstream tasks, are often regarded as a black box and used as a whole. It is still unclear what mechanisms they have learned, especially their core module:…

Neural networks are growing more capable on their own, but we do not understand their neural mechanisms. Understanding these mechanisms' decision-making processes, or mechanistic interpretability, enables (1) accountability and control in…

Mechanistic interpretability research seeks to reveal the inner workings of large language models, yet most work focuses on classification or generative tasks rather than summarization. This paper presents an interpretability framework for…

Human attention modelling has proven, in recent years, to be particularly useful not only for understanding the cognitive processes underlying visual exploration, but also for providing support to artificial intelligence models that aim to…