English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The behavior of deep neural networks (DNNs) is hard to understand. This makesit necessary to explore post hoc explanation methods. We conduct the firstcomprehensive evaluation of explanation methods for NLP. To this end, we designtwo novel evaluation paradigms that cover two important classes of NLPproblems: small context and large context problems. Both paradigms require nomanual annotation and are therefore broadly applicable. We also introduceLIMSSE, an explanation method inspired by LIME that is designed for NLP. Weshow empirically that LIMSSE, LRP and DeepLIFT are the most effectiveexplanation methods and recommend them for explaining DNNs in NLP.

Evaluating neural network explanation methods using hybrid documents and morphological agreement