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

Compositional generalization is a fundamental trait in humans, allowing us toeffortlessly combine known phrases to form novel sentences. Recent works haveclaimed that standard seq-to-seq models severely lack the ability tocompositionally generalize. In this paper, we focus on one-shot primitivegeneralization as introduced by the popular SCAN benchmark. We demonstrate thatmodifying the training distribution in simple and intuitive ways enablesstandard seq-to-seq models to achieve near-perfect generalization performance,thereby showing that their compositional generalization abilities werepreviously underestimated. We perform detailed empirical analysis of thisphenomenon. Our results indicate that the generalization performance of modelsis highly sensitive to the characteristics of the training data which should becarefully considered while designing such benchmarks in future.

Revisiting the Compositional Generalization Abilities of Neural Sequence Models