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

Transformers are widely used in natural language processing, where theyconsistently achieve state-of-the-art performance. This is mainly due to theirattention-based architecture, which allows them to model rich linguisticrelations between (sub)words. However, transformers are difficult to interpret.Being able to provide reasoning for its decisions is an important property fora model in domains where human lives are affected. With transformers findingwide use in such fields, the need for interpretability techniques tailored tothem arises. We propose a new technique that selects the most faithfulattention-based interpretation among the several ones that can be obtained bycombining different head, layer and matrix operations. In addition, twovariations are introduced towards (i) reducing the computational complexity,thus being faster and friendlier to the environment, and (ii) enhancing theperformance in multi-label data. We further propose a new faithfulness metricthat is more suitable for transformer models and exhibits high correlation withthe area under the precision-recall curve based on ground truth rationales. Wevalidate the utility of our contributions with a series of quantitative andqualitative experiments on seven datasets.

An Attention Matrix for Every Decision: Faithfulness-based Arbitration  Among Multiple Attention-Based Interpretations of Transformers in Text  Classification