Bootstrapping Multilingual Semantic Parsers using Large Language Models

Abstract

Despite cross-lingual generalization demonstrated by pre-trained multilingual models, the translate-train paradigm of transferring English datasets across multiple languages remains to be a key mechanism for training taskspecific multilingual models. However, for many low-resource languages, the availability of a reliable translation service entails significant amounts of costly human-annotated translation pairs. Further, translation services may continue to be brittle due to domain mismatch between task-specific input text and generalpurpose text used for training translation models. For multilingual semantic parsing, we demonstrate the effectiveness and flexibility offered by large language models (LLMs) for translating English datasets into several languages via few-shot prompting. Through extensive comparisons on two public datasets, MTOP and MASSIVE, spanning 50 languages and several domains, we show that our method of translating data using LLMs outperforms a strong translate-train baseline on 41 out of 50 languages. We study the key design choices that enable more effective multilingual data translation via prompted LLMs.

ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters

“…In the future, our approach, being task-agnostic, can be applied to more non-trivial tasks, such as generation (Kolluru et al, 2022(Kolluru et al, , 2021, semantic parsing (Awasthi et al, 2023), relation extraction (Rathore et al, 2022Bhartiya et al, 2022), and knowledge graph completion Mittal et al, 2023). Our technique may complement other approaches for morphologically rich languages (Nzeyimana and Rubungo, 2022) and for 7 https://github.com/dair-iitd/ZGUL those with scripts unseen in mBERT (Pfeiffer et al, 2021b).…”