Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages

Anonymous

Paper Type: short

Keywords: Cross-lingual, DGDS

TL;DR: we enhances low-resource languages in document-grounded dialogue systems by leveraging high-resource languages and incorporating adversarial training and a new training architecture.

Abstract: This paper proposes a framework to address the issue of data scarcity in Document-Grounded Dialogue Systems(DGDS). Our model leverages high-resource languages to enhance the capability of dialogue generation in low-resource languages. Specifically, We present a novel pipeline CLEM (Cross-Lingual Enhanced Model) including adversarial training retrieval (Retriever and Re-ranker), and Fid (fusion-in-decoder) generator. To further leverage high-resource language, we also propose an innovative architecture to conduct alignment across different languages with translated training. Extensive experiment results demonstrate the effectiveness of our model and we achieved 4th place in the DialDoc 2023 Competition. Therefore, CLEM can serve as a solution to resource scarcity in DGDS and provide useful guidance for multi-lingual alignment tasks.