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

Existing metrics for assessing question generation not only require costlyhuman reference but also fail to take into account the input context ofgeneration, rendering the lack of deep understanding of the relevance betweenthe generated questions and input contexts. As a result, they may wronglypenalize a legitimate and reasonable candidate question when it (i) involvescomplicated reasoning with the context or (ii) can be grounded by multipleevidences in the context. In this paper, we propose $\textbf{QRelScore}$, acontext-aware $\underline{\textbf{Rel}}$evance evaluation metric for$\underline{\textbf{Q}}$uestion Generation. Based on off-the-shelf languagemodels such as BERT and GPT2, QRelScore employs both word-level hierarchicalmatching and sentence-level prompt-based generation to cope with thecomplicated reasoning and diverse generation from multiple evidences,respectively. Compared with existing metrics, our experiments demonstrate thatQRelScore is able to achieve a higher correlation with human judgments whilebeing much more robust to adversarial samples.

QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance