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
- 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)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2022.acl-long.285.pdf
- Code
- tomsherborne/zx-parse
- Data
- ATIS, MKQA, ParaCrawl