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

Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang, Iryna Gurevych


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.
Anthology ID:
2021.emnlp-main.57
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
742–750
Language:
URL:
https://aclanthology.org/2021.emnlp-main.57
DOI:
10.18653/v1/2021.emnlp-main.57
Bibkey:
Cite (ACL):
Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang, and Iryna Gurevych. 2021. Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 742–750, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation (Ribeiro et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.57.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.57.mp4
Code
 ukplab/m-amr2text