Online and Linear-Time Attention by Enforcing Monotonic Alignments

TL;DR

This paper introduces a differentiable method for learning monotonic alignments in sequence-to-sequence models, enabling online, linear-time attention computation suitable for real-time applications.

Contribution

The authors propose a novel end-to-end differentiable approach for monotonic attention that allows online and efficient attention computation in sequence models.

Findings

Achieves competitive results on sentence summarization, machine translation, and speech recognition.

Enables online attention computation with linear time complexity.

Outperforms traditional soft attention in online settings.

Abstract

Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input sequence when producing each element in the output sequence precludes their use in online settings and results in a quadratic time complexity. Based on the insight that the alignment between input and output sequence elements is monotonic in many problems of interest, we propose an end-to-end differentiable method for learning monotonic alignments which, at test time, enables computing attention online and in linear time. We validate our approach on sentence summarization, machine translation, and online speech recognition problems and achieve results competitive with existing sequence-to-sequence models.