Log In Sign Up

A Regularized Framework for Sparse and Structured Neural Attention

by   Vlad Niculae, et al.

Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max operator. We show that the gradient of this operator defines a mapping from real values to probabilities, suitable as an attention mechanism. Our framework includes softmax and a slight generalization of the recently-proposed sparsemax as special cases. However, we also show how our framework can incorporate modern structured penalties, resulting in more interpretable attention mechanisms, that focus on entire segments or groups of an input. We derive efficient algorithms to compute the forward and backward passes of our attention mechanisms, enabling their use in a neural network trained with backpropagation. To showcase their potential as a drop-in replacement for existing ones, we evaluate our attention mechanisms on three large-scale tasks: textual entailment, machine translation, and sentence summarization. Our attention mechanisms improve interpretability without sacrificing performance; notably, on textual entailment and summarization, we outperform the standard attention mechanisms based on softmax and sparsemax.


page 13

page 16

page 17

page 19

page 20

page 21


A Cheap Linear Attention Mechanism with Fast Lookups and Fixed-Size Representations

The softmax content-based attention mechanism has proven to be very bene...

Contrastive Attention Mechanism for Abstractive Sentence Summarization

We propose a contrastive attention mechanism to extend the sequence-to-s...

On Controllable Sparse Alternatives to Softmax

Converting an n-dimensional vector to a probability distribution over n ...

Salience Estimation with Multi-Attention Learning for Abstractive Text Summarization

Attention mechanism plays a dominant role in the sequence generation mod...

From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification

We propose sparsemax, a new activation function similar to the tradition...

A^3: Accelerating Attention Mechanisms in Neural Networks with Approximation

With the increasing computational demands of neural networks, many hardw...

Understanding Multi-Head Attention in Abstractive Summarization

Attention mechanisms in deep learning architectures have often been used...

Code Repositories


Sparse and structured neural attention mechanisms

view repo