2017 LearningWhentoSkimandWhentoRead

(Johansen & Socher, 2017) ⇒ Alexander Johansen, and Richard Socher. (2017). “Learning When to Skim and When to Read.” In: Proceedings of the 2nd Workshop on Representation Learning for {NLP}.

Subject Headings: Skim-Reading Task; Bag-Of-Words Skim-Reading Task; LSTM Skim-Reading Task.

Notes

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.

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2017 LearningWhentoSkimandWhentoRead	Richard Socher Alexander Johansen			Learning When to Skim and When to Read