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

Evaluating neural network explanation methods using hybrid documents and morphological agreement

2019-05-06
Nina Poerner, Benjamin Roth, Hinrich Schütze

Abstract

The behavior of deep neural networks (DNNs) is hard to understand. This makes it necessary to explore post hoc explanation methods. We conduct the first comprehensive evaluation of explanation methods for NLP. To this end, we design two novel evaluation paradigms that cover two important classes of NLP problems: small context and large context problems. Both paradigms require no manual annotation and are therefore broadly applicable. We also introduce LIMSSE, an explanation method inspired by LIME that is designed for NLP. We show empirically that LIMSSE, LRP and DeepLIFT are the most effective explanation methods and recommend them for explaining DNNs in NLP.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1801.06422

PDF

http://arxiv.org/pdf/1801.06422


Comments

Content