papers AI Learner
The Github is limit! Click to go to the new site.

No Training Required: Exploring Random Encoders for Sentence Classification

2019-01-29
John Wieting, Douwe Kiela

Abstract

We explore various methods for computing sentence representations from pre-trained word embeddings without any training, i.e., using nothing but random parameterizations. Our aim is to put sentence embeddings on more solid footing by 1) looking at how much modern sentence embeddings gain over random methods—as it turns out, surprisingly little; and by 2) providing the field with more appropriate baselines going forward—which are, as it turns out, quite strong. We also make important observations about proper experimental protocol for sentence classification evaluation, together with recommendations for future research.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.10444

PDF

http://arxiv.org/pdf/1901.10444


Similar Posts

Comments