Cross-Lingual Transfer for Natural Language Inference via Multilingual Prompt Translator

arXiv:2403.12407v1 Announce Type: new
Abstract: Based on multilingual pre-trained models, cross-lingual transfer with prompt learning has shown promising effectiveness, where soft prompt learned in a source language is transferred to target languages for downstream tasks, particularly in the low-resource scenario. To efficiently transfer soft prompt, we propose a novel framework, Multilingual Prompt Translator (MPT), where a multilingual prompt translator is introduced to properly process crucial knowledge embedded in prompt by changing language knowledge while retaining task knowledge. Concretely, we first …

abstract arxiv cross-lingual cs.cl framework inference language languages low multilingual natural natural language novel pre-trained models prompt prompt learning tasks transfer type via