Comparison of Cross-lingual Strategies for AMR-to-Brazilian Portuguese Generation
Preprint
- 11 November 2022
- preprint
- Published by Springer Nature in Research Square
Abstract
This work presents a study of different strategies for tackling low-resource AMR-to-text generation for Brazilian Portuguese on three approaches. In particular, we explore the use of English AMR as an interlingua and transfer learning (TL). The results suggest that using AMR as an interlingua can be a strong baseline. However, we need to consider the bilingual dictionary used in the concept translation, as it can harm text generation. On the other hand, TL seems to be a promising strategy for generating accurate outputs, but its contribution is not significant. Finally, we present a transformer-based model with the best performance, surpassing all baselines.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Investigating Pretrained Language Models for Graph-to-Text Generation2021
- Semantic Neural Machine Translation Using AMRTransactions of the Association for Computational Linguistics, 2019
- Domain Transfer for Deep Natural Language Generation from Abstract Meaning RepresentationsIEEE Computational Intelligence Magazine, 2017
- Expressive Power of Abstract Meaning RepresentationsComputational Linguistics, 2016
- The Proposition Bank: An Annotated Corpus of Semantic RolesComputational Linguistics, 2005