English

Zero-Shot Cross-lingual Semantic Parsing

Computation and Language 2022-03-08 v2

Abstract

Recent work in cross-lingual semantic parsing has successfully applied machine translation to localize parsers to new languages. However, these advances assume access to high-quality machine translation systems and word alignment tools. We remove these assumptions and study cross-lingual semantic parsing as a zero-shot problem, without parallel data (i.e., utterance-logical form pairs) for new languages. We propose a multi-task encoder-decoder model to transfer parsing knowledge to additional languages using only English-logical form paired data and in-domain natural language corpora in each new language. Our model encourages language-agnostic encodings by jointly optimizing for logical-form generation with auxiliary objectives designed for cross-lingual latent representation alignment. Our parser performs significantly above translation-based baselines and, in some cases, competes with the supervised upper-bound.

Keywords

Cite

@article{arxiv.2104.07554,
  title  = {Zero-Shot Cross-lingual Semantic Parsing},
  author = {Tom Sherborne and Mirella Lapata},
  journal= {arXiv preprint arXiv:2104.07554},
  year   = {2022}
}

Comments

Accepted to ACL2022 Main Conference. 19 pages, 3 figures, 12 tables

R2 v1 2026-06-24T01:12:25.418Z