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

Localizing a semantic parser to support new languages requires effectivecross-lingual generalization. Recent work has found success withmachine-translation or zero-shot methods although these approaches can struggleto model how native speakers ask questions. We consider how to effectivelyleverage minimal annotated examples in new languages for few-shot cross-lingualsemantic parsing. We introduce a first-order meta-learning algorithm to train asemantic parser with maximal sample efficiency during cross-lingual transfer.Our algorithm uses high-resource languages to train the parser andsimultaneously optimizes for cross-lingual generalization for lower-resourcelanguages. Results across six languages on ATIS demonstrate that ourcombination of generalization steps yields accurate semantic parsers sampling$\le$10% of source training data in each new language. Our approach also trainsa competitive model on Spider using English with generalization to Chinesesimilarly sampling $\le$10% of training data.

Meta-Learning a Cross-lingual Manifold for Semantic Parsing