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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Transformer architectures are complex and their use in NLP, while it hasengendered many successes, makes their interpretability or explainabilitychallenging. Recent debates have shown that attention maps and attributionmethods are unreliable (Pruthi et al., 2019; Brunner et al., 2019). In thispaper, we present some of their limitations and introduce COCKATIEL, whichsuccessfully addresses some of them. COCKATIEL is a novel, post-hoc,concept-based, model-agnostic XAI technique that generates meaningfulexplanations from the last layer of a neural net model trained on an NLPclassification task by using Non-Negative Matrix Factorization (NMF) todiscover the concepts the model leverages to make predictions and by exploitinga Sensitivity Analysis to estimate accurately the importance of each of theseconcepts for the model. It does so without compromising the accuracy of theunderlying model or requiring a new one to be trained. We conduct experimentsin single and multi-aspect sentiment analysis tasks and we show COCKATIEL'ssuperior ability to discover concepts that align with humans' on Transformermodels without any supervision, we objectively verify the faithfulness of itsexplanations through fidelity metrics, and we showcase its ability to providemeaningful explanations in two different datasets.

COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks