Related papers: Learning compositionally through attentive guidanc…

Recommender Systems are an integral part of music sharing platforms. Often the aim of these systems is to increase the time, the user spends on the platform and hence having a high commercial value. The systems which aim at increasing the…

Knowledge tracing aims to model students' past answer sequences to track the change in their knowledge acquisition during exercise activities and to predict their future learning performance. Most existing approaches ignore the fact that…

The transduction of sequence has been mostly done by recurrent networks, which are computationally demanding and often underestimate uncertainty severely. We propose a computationally efficient attention-based network combined with the…

Humans excel at applying learned behavior to unlearned situations. A crucial component of this generalization behavior is our ability to compose/decompose a whole into reusable parts, an attribute known as compositionality. One of the…

We consider the problem of learning causal directed acyclic graphs from an observational joint distribution. One can use these graphs to predict the outcome of interventional experiments, from which data are often not available. We show…

Collaborative reasoning for understanding image-question pairs is a very critical but underexplored topic in interpretable visual question answering systems. Although very recent studies have attempted to use explicit compositional…

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from…

We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting. Inspired by neurophysiological evidence that the primary visual cortex does not…

The task of predicting dialog acts (DA) based on conversational dialog is a key component in the development of conversational agents. Accurately predicting DAs requires a precise modeling of both the conversation and the global tag…

Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components.…

We introduce a new approach to functional causal modeling from observational data, called Causal Generative Neural Networks (CGNN). CGNN leverages the power of neural networks to learn a generative model of the joint distribution of the…

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits…

Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e.g., relative positions and poses). In this paper, we…

Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…

Neural networks can be powerful function approximators, which are able to model high-dimensional feature distributions from a subset of examples drawn from the target distribution. Naturally, they perform well at generalizing within the…

We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents. Our alignment-based encoder-decoder model with long short-term memory recurrent neural networks…

Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components observed during…

Attention is a very efficient way to model the relationship between two sequences by comparing how similar two intermediate representations are. Initially demonstrated in NMT, it is a standard in all NLU tasks today when efficient…

Self-attention is an attention mechanism that learns a representation by relating different positions in the sequence. The transformer, which is a sequence model solely based on self-attention, and its variants achieved state-of-the-art…

The attentional mechanism has proven to be effective in improving end-to-end neural machine translation. However, due to the intricate structural divergence between natural languages, unidirectional attention-based models might only capture…