# Learning when to skim and when to read

arXiv: https://arxiv.org/abs/1712.05483 · HTML: https://mlsanity.com/paper/1712.05483/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2017.

## Built on by (most cited first, 1 of 1)

- [Efficient Nearest Neighbor Language Models](https://mlsanity.com/paper/2109.04212/) (2021)

## Abstract (arXiv)

Many recent advances in deep learning for natural language processing have come at increasing computational cost, but the power of these state-of-the-art models is not needed for every example in a dataset. We demonstrate two approaches to reducing unnecessary computation in cases where a fast but weak baseline classier and a stronger, slower model are both available. Applying an AUC-based metric to the task of sentiment classification, we find significant efficiency gains with both a probability-threshold method for reducing computational cost and one that uses a secondary decision network.