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

Language grounding aims at linking the symbolic representation of language(e.g., words) into the rich perceptual knowledge of the outside world. Thegeneral approach is to embed both textual and visual information into a commonspace -the grounded space-confined by an explicit relationship between bothmodalities. We argue that this approach sacrifices the abstract knowledgeobtained from linguistic co-occurrence statistics in the process of acquiringperceptual information. The focus of this paper is to solve this issue byimplicitly grounding the word embeddings. Rather than learning two mappingsinto a joint space, our approach integrates modalities by determining areversible grounded mapping between the textual and the grounded space by meansof multi-task learning. Evaluations on intrinsic and extrinsic tasks show thatour embeddings are highly beneficial for both abstract and concrete words. Theyare strongly correlated with human judgments and outperform previous works on awide range of benchmarks. Our grounded embeddings are publicly available here.

Learning Zero-Shot Multifaceted Visually Grounded Word Embeddings via Multi-Task Training