Meta-Learning a Cross-lingual Manifold for Semantic Parsing
This work addresses the challenge of localizing semantic parsers for new languages with minimal annotated data, which is incremental as it builds on existing cross-lingual methods.
The paper tackles the problem of few-shot cross-lingual semantic parsing by introducing a first-order meta-learning algorithm that leverages high-resource languages to train a parser and optimizes for generalization to lower-resource languages, achieving accurate parsers with ≤10% of source training data in new languages on ATIS and Spider datasets.
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 optimizes for cross-lingual generalization for lower-resource languages. Results across six languages on ATIS demonstrate that our combination of generalization steps yields accurate semantic parsers sampling $\le$10% of source training data in each new language. Our approach also trains a competitive model on Spider using English with generalization to Chinese similarly sampling $\le$10% of training data.