Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation

TL;DR

This paper explores methods for automatically generating AMR annotations to improve multilingual AMR-to-text generation, demonstrating that combining gold and silver data enhances performance across multiple languages.

Contribution

It introduces techniques for generating AMR annotations from different sources and shows that combining gold and silver data outperforms existing approaches.

Findings

Models trained on gold AMR with silver sentences outperform those using only silver AMR.

Combining gold and silver sources further improves multilingual AMR-to-text results.

The approach surpasses previous state-of-the-art in German, Italian, Spanish, and Chinese.

Abstract

Recent work on multilingual AMR-to-text generation has exclusively focused on data augmentation strategies that utilize silver AMR. However, this assumes a high quality of generated AMRs, potentially limiting the transferability to the target task. In this paper, we investigate different techniques for automatically generating AMR annotations, where we aim to study which source of information yields better multilingual results. Our models trained on gold AMR with silver (machine translated) sentences outperform approaches which leverage generated silver AMR. We find that combining both complementary sources of information further improves multilingual AMR-to-text generation. Our models surpass the previous state of the art for German, Italian, Spanish, and Chinese by a large margin.