Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data

TL;DR

This paper introduces the Translate-and-Fill method, a zero-shot data augmentation technique that enhances multilingual semantic parsing by generating synthetic training data using a sequence-to-sequence filler trained only on English.

Contribution

The paper presents a simplified, effective Translate-and-Fill approach that improves multilingual semantic parsing without relying on complex alignment, outperforming traditional methods.

Findings

TaF achieves competitive accuracy with traditional alignment-based systems.

The method effectively generalizes to multiple languages in zero-shot settings.

Data augmentation with TaF improves semantic parsing performance.

Abstract

While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when target language supervision is available. In this paper, we propose a novel Translate-and-Fill (TaF) method to produce silver training data for a multilingual semantic parser. This method simplifies the popular Translate-Align-Project (TAP) pipeline and consists of a sequence-to-sequence filler model that constructs a full parse conditioned on an utterance and a view of the same parse. Our filler is trained on English data only but can accurately complete instances in other languages (i.e., translations of the English training utterances), in a zero-shot fashion. Experimental results on three multilingual semantic parsing datasets show that data augmentation with TaF reaches accuracies competitive with similar systems which rely on traditional alignment techniques.