Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing

TL;DR

This paper introduces Cross-Lingual Back-Parsing (CBP), a novel data augmentation method that synthesizes target language utterances from meaning representations to improve zero-resource cross-lingual semantic parsing.

Contribution

The paper proposes CBP, a new approach leveraging mPLM geometry to generate target language data from source meaning representations, enhancing zero-shot cross-lingual transfer.

Findings

CBP significantly improves target language performance on SP benchmarks.

Synthesized utterances maintain high slot value alignment and semantic integrity.

Method is effective using only source labeled data and monolingual corpora.

Abstract

Recent efforts have aimed to utilize multilingual pretrained language models (mPLMs) to extend semantic parsing (SP) across multiple languages without requiring extensive annotations. However, achieving zero-shot cross-lingual transfer for SP remains challenging, leading to a performance gap between source and target languages. In this study, we propose Cross-Lingual Back-Parsing (CBP), a novel data augmentation methodology designed to enhance cross-lingual transfer for SP. Leveraging the representation geometry of the mPLMs, CBP synthesizes target language utterances from source meaning representations. Our methodology effectively performs cross-lingual data augmentation in challenging zero-resource settings, by utilizing only labeled data in the source language and monolingual corpora. Extensive experiments on two cross-language SP benchmarks (Mschema2QA and Xspider) demonstrate that CBP brings substantial gains in the target language. Further analysis of the synthesized utterances shows that our method successfully generates target language utterances with high slot value alignment rates while preserving semantic integrity. Our codes and data are publicly available at https://github.com/deokhk/CBP.