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

Hyperbole, or exaggeration, is a common linguistic phenomenon. The detectionof hyperbole is an important part of understanding human expression. There havebeen several studies on hyperbole detection, but most of which focus on textmodality only. However, with the development of social media, people can createhyperbolic expressions with various modalities, including text, images, videos,etc. In this paper, we focus on multimodal hyperbole detection. We create amultimodal detection dataset\footnote{The dataset will be released to thecommunity.} from Weibo (a Chinese social media) and carry out some studies onit. We treat the text and image from a piece of weibo as two modalities andexplore the role of text and image for hyperbole detection. Differentpre-trained multimodal encoders are also evaluated on this downstream task toshow their performance. Besides, since this dataset is constructed from fivedifferent topics, we also evaluate the cross-domain performance of differentmodels. These studies can serve as a benchmark and point out the direction offurther study on multimodal hyperbole detection.

Image Matters: A New Dataset and Empirical Study for Multimodal Hyperbole Detection