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

Recently, state-of-the-art NLP models gained an increasing syntactic andsemantic understanding of language, and explanation methods are crucial tounderstand their decisions. Occlusion is a well established method thatprovides explanations on discrete language data, e.g. by removing a languageunit from an input and measuring the impact on a model's decision. We arguethat current occlusion-based methods often produce invalid or syntacticallyincorrect language data, neglecting the improved abilities of recent NLPmodels. Furthermore, gradient-based explanation methods disregard the discretedistribution of data in NLP. Thus, we propose OLM: a novel explanation methodthat combines occlusion and language models to sample valid and syntacticallycorrect replacements with high likelihood, given the context of the originalinput. We lay out a theoretical foundation that alleviates these weaknesses ofother explanation methods in NLP and provide results that underline theimportance of considering data likelihood in occlusion-based explanation.

Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling