# Learning to Skim Text

## TL;DR

This paper introduces a recurrent neural network model that learns to skip irrelevant parts of text, significantly speeding up processing of long documents while maintaining or improving accuracy.

## Contribution

It proposes a novel LSTM-based model with learned jumping behavior, trained via policy gradients, to efficiently read and analyze long texts.

## Key findings

- Up to 6 times faster than standard LSTMs on multiple tasks
- Maintains or improves accuracy despite skipping parts of text
- Effective across diverse NLP tasks such as sentiment analysis and Q&A

## Abstract

Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models have to read the whole text word by word, making it slow to handle long documents. For example, it is difficult to use a recurrent network to read a book and answer questions about it. In this paper, we present an approach of reading text while skipping irrelevant information if needed. The underlying model is a recurrent network that learns how far to jump after reading a few words of the input text. We employ a standard policy gradient method to train the model to make discrete jumping decisions. In our benchmarks on four different tasks, including number prediction, sentiment analysis, news article classification and automatic Q\&A, our proposed model, a modified LSTM with jumping, is up to 6 times faster than the standard sequential LSTM, while maintaining the same or even better accuracy.