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

Multimodal Sarcasm Understanding (MSU) has a wide range of applications inthe news field such as public opinion analysis and forgery detection. However,existing MSU benchmarks and approaches usually focus on sentence-level MSU. Indocument-level news, sarcasm clues are sparse or small and are often concealedin long text. Moreover, compared to sentence-level comments like tweets, whichmainly focus on only a few trends or hot topics (e.g., sports events), contentin the news is considerably diverse. Models created for sentence-level MSU mayfail to capture sarcasm clues in document-level news. To fill this gap, wepresent a comprehensive benchmark for Document-level Multimodal SarcasmUnderstanding (DocMSU). Our dataset contains 102,588 pieces of news withtext-image pairs, covering 9 diverse topics such as health, business, etc. Theproposed large-scale and diverse DocMSU significantly facilitates the researchof document-level MSU in real-world scenarios. To take on the new challengesposed by DocMSU, we introduce a fine-grained sarcasm comprehension method toproperly align the pixel-level image features with word-level textual featuresin documents. Experiments demonstrate the effectiveness of our method, showingthat it can serve as a baseline approach to the challenging DocMSU. Our codeand dataset are available at https://github.com/Dulpy/DocMSU.

DocMSU: A Comprehensive Benchmark for Document-level Multimodal Sarcasm Understanding