Logo Logo
Switch Language to German
Poerner, Nina; Roth, Benjamin; Schütze, Hinrich (July 2018): Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement. The 56th Annual Meeting of the Association for Computational Linguistics, 15. - 20. July 2018, Melbourne, Australia.


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 mosteffective explanation methods and recommend them for explaining DNNs in NLP.