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

Gradient-based explanation methods play an important role in the field ofinterpreting complex deep neural networks for NLP models. However, the existingwork has shown that the gradients of a model are unstable and easilymanipulable, which impacts the model's reliability largely. According to ourpreliminary analyses, we also find the interpretability of gradient-basedmethods is limited for complex tasks, such as aspect-based sentimentclassification (ABSC). In this paper, we propose an\textbf{I}nterpretation-\textbf{E}nhanced \textbf{G}radient-based framework for\textbf{A}BSC via a small number of explanation annotations, namely\texttt{{IEGA}}. Particularly, we first calculate the word-level saliency mapbased on gradients to measure the importance of the words in the sentencetowards the given aspect. Then, we design a gradient correction module toenhance the model's attention on the correct parts (e.g., opinion words). Ourmodel is model agnostic and task agnostic so that it can be integrated into theexisting ABSC methods or other tasks. Comprehensive experimental results onfour benchmark datasets show that our \texttt{IEGA} can improve not only theinterpretability of the model but also the performance and robustness.

Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations