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

Interpretable Textual Neuron Representations for NLP

2018-09-19
Nina Poerner, Benjamin Roth, Hinrich Schütze

Abstract

Input optimization methods, such as Google Deep Dream, create interpretable representations of neurons for computer vision DNNs. We propose and evaluate ways of transferring this technology to NLP. Our results suggest that gradient ascent with a gumbel softmax layer produces n-gram representations that outperform naive corpus search in terms of target neuron activation. The representations highlight differences in syntax awareness between the language and visual models of the Imaginet architecture.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1809.07291

PDF

https://arxiv.org/pdf/1809.07291


Similar Posts

Comments