GPT-too: A language-model-first approach for AMR-to-text generation
This work addresses text generation from semantic graphs for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackled the problem of generating text from Abstract Meaning Representations (AMRs) by proposing a language-model-first approach with cycle consistency-based re-scoring, achieving state-of-the-art performance on the English LDC2017T10 dataset and validating results through human evaluation.
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.