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

We analyze the grounded SCAN (gSCAN) benchmark, which was recently proposedto study systematic generalization for grounded language understanding. First,we study which aspects of the original benchmark can be solved by commonly usedmethods in multi-modal research. We find that a general-purposeTransformer-based model with cross-modal attention achieves strong performanceon a majority of the gSCAN splits, surprisingly outperforming more specializedapproaches from prior work. Furthermore, our analysis suggests that many of theremaining errors reveal the same fundamental challenge in systematicgeneralization of linguistic constructs regardless of visual context. Second,inspired by this finding, we propose challenging new tasks for gSCAN bygenerating data to incorporate relations between objects in the visualenvironment. Finally, we find that current models are surprisingly datainefficient given the narrow scope of commands in gSCAN, suggesting anotherchallenge for future work.

Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?