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/

Zendy Plus

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

Zendy Tools

Zendy Open

Grounding language in contextual information is crucial for fine-grainednatural language understanding. One important task that involves groundingcontextual modifiers is color generation. Given a reference color "green", anda modifier "bluey", how does one generate a color that could represent "blueygreen"? We propose a computational pragmatics model that formulates this colorgeneration task as a recursive game between speakers and listeners. In ourmodel, a pragmatic speaker reasons about the inferences that a listener wouldmake, and thus generates a modified color that is maximally informative to helpthe listener recover the original referents. In this paper, we show thatincorporating pragmatic information provides significant improvements inperformance compared with other state-of-the-art deep learning models wherepragmatic inference and flexibility in representing colors from a largecontinuous space are lacking. Our model has an absolute 98% increase inperformance for the test cases where the reference colors are unseen duringtraining, and an absolute 40% increase in performance for the test cases whereboth the reference colors and the modifiers are unseen during training.

Pragmatically Informative Color Generation by Grounding Contextual Modifiers