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

Multi-modal sarcasm detection has attracted much recent attention.Nevertheless, the existing benchmark (MMSD) has some shortcomings that hinderthe development of reliable multi-modal sarcasm detection system: (1) There aresome spurious cues in MMSD, leading to the model bias learning; (2) Thenegative samples in MMSD are not always reasonable. To solve the aforementionedissues, we introduce MMSD2.0, a correction dataset that fixes the shortcomingsof MMSD, by removing the spurious cues and re-annotating the unreasonablesamples. Meanwhile, we present a novel framework called multi-view CLIP that iscapable of leveraging multi-grained cues from multiple perspectives (i.e.,text, image, and text-image interaction view) for multi-modal sarcasmdetection. Extensive experiments show that MMSD2.0 is a valuable benchmark forbuilding reliable multi-modal sarcasm detection systems and multi-view CLIP cansignificantly outperform the previous best baselines.

MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System