Meta-Learning a Cross-lingual Manifold for Semantic Parsing. (arXiv:2209.12577v2 [cs.CL] UPDATED)

Localizing a semantic parser to support new languages requires effective
cross-lingual generalization. Recent work has found success with
machine-translation or zero-shot methods although these approaches can struggle
to model how native speakers ask questions. We consider how to effectively
leverage minimal annotated examples in new languages for few-shot cross-lingual
semantic parsing. We introduce a first-order meta-learning algorithm to train a
semantic parser with maximal sample efficiency during cross-lingual transfer.
Our algorithm uses high-resource languages to train the parser and
simultaneously …

arxiv cross-lingual manifold meta meta-learning parsing semantic