GPT-too: A language-model-first approach for AMR-to-text generation
Abstract
Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequence-to-sequence or graph-to-sequence models on AMR annotated data only. In this paper, we propose an alternative approach that combines a strong pre-trained language model with cycle consistency-based re-scoring. Despite the simplicity of the approach, our experimental results show these models outperform all previous techniques on the English LDC2017T10dataset, including the recent use of transformer architectures. In addition to the standard evaluation metrics, we provide human evaluation experiments that further substantiate the strength of our approach.
Cite
@article{arxiv.2005.09123,
title = {GPT-too: A language-model-first approach for AMR-to-text generation},
author = {Manuel Mager and Ramon Fernandez Astudillo and Tahira Naseem and Md Arafat Sultan and Young-Suk Lee and Radu Florian and Salim Roukos},
journal= {arXiv preprint arXiv:2005.09123},
year = {2020}
}
Comments
Paper accepted to the Annual Meeting of the Association for Computational Linguistics (ACL 2020)