# Sequential Attention: A Context-Aware Alignment Function for Machine Reading

## TL;DR

This paper introduces a Sequential Attention layer that enhances neural reading models by considering surrounding words for better context-aware alignment, significantly improving reading comprehension performance.

## Contribution

It presents a novel Sequential Attention mechanism that extends soft attention to incorporate context from neighboring words, advancing neural reading comprehension models.

## Key findings

- Significant performance improvement over the Stanford Reader baseline
- Competitive results on Who did What and CNN datasets
- Effective context-aware attention mechanism

## Abstract

In this paper we propose a neural network model with a novel Sequential Attention layer that extends soft attention by assigning weights to words in an input sequence in a way that takes into account not just how well that word matches a query, but how well surrounding words match. We evaluate this approach on the task of reading comprehension (on the Who did What and CNN datasets) and show that it dramatically improves a strong baseline--the Stanford Reader--and is competitive with the state of the art.