Abstract
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 to lower-resource languages. Results across six languages on ATIS demonstrate that our combination of generalization steps yields accurate semantic parsers sampling ≤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 ≤10% of training data.1- Anthology ID:
- 2023.tacl-1.4
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 11
- Month:
- Year:
- 2023
- Address:
- Cambridge, MA
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 49–67
- Language:
- URL:
- https://aclanthology.org/2023.tacl-1.4
- DOI:
- 10.1162/tacl_a_00533
- Cite (ACL):
- Tom Sherborne and Mirella Lapata. 2023. Meta-Learning a Cross-lingual Manifold for Semantic Parsing. Transactions of the Association for Computational Linguistics, 11:49–67.
- Cite (Informal):
- Meta-Learning a Cross-lingual Manifold for Semantic Parsing (Sherborne & Lapata, TACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.tacl-1.4.pdf