Litcius/Paper detail

Zero-Shot Cross-lingual Semantic Parsing

Tom Sherborne, Mirella Lapata

2022Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)25 citationsDOIOpen Access PDF

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 highquality 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 encoderdecoder model to transfer parsing knowledge to additional languages using only Englishlogical 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. 1

Topics & Concepts

Computer scienceNatural language processingParsingArtificial intelligenceLogical formMachine translationTask (project management)Top-down parsingBottom-up parsingUtteranceTop-down parsing languageEncoderTranslation (biology)S-attributed grammarChemistryEconomicsManagementOperating systemMessenger RNABiochemistryGeneNatural Language Processing TechniquesTopic ModelingMultimodal Machine Learning Applications