Zero-Shot Cross-lingual Semantic Parsing

Tom Sherborne, Mirella Lapata


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.
Anthology ID:
2022.acl-long.285
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4134–4153
Language:
URL:
https://aclanthology.org/2022.acl-long.285
DOI:
10.18653/v1/2022.acl-long.285
Bibkey:
Cite (ACL):
Tom Sherborne and Mirella Lapata. 2022. Zero-Shot Cross-lingual Semantic Parsing. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4134–4153, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Cross-lingual Semantic Parsing (Sherborne & Lapata, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.285.pdf
Software:
 2022.acl-long.285.software.zip
Video:
 https://aclanthology.org/2022.acl-long.285.mp4
Video:
 https://aclanthology.org/2022.acl-long.285.mp4
Code
 tomsherborne/zx-parse
Data
ATISMKQAParaCrawl