Structural Neural Encoders for AMR-to-text Generation
This work addresses the problem of generating natural language sentences from AMR graphs for NLP researchers, offering incremental improvements over existing methods.
The paper tackled AMR-to-text generation by comparing graph encoders to tree encoders, showing that handling reentrancies and long-range dependencies improves performance, with their best model achieving 24.40 BLEU on LDC2015E86 and 24.54 BLEU on LDC2017T10, outperforming state-of-the-art by 1.1 and 1.24 points respectively.
AMR-to-text generation is a problem recently introduced to the NLP community, in which the goal is to generate sentences from Abstract Meaning Representation (AMR) graphs. Sequence-to-sequence models can be used to this end by converting the AMR graphs to strings. Approaching the problem while working directly with graphs requires the use of graph-to-sequence models that encode the AMR graph into a vector representation. Such encoding has been shown to be beneficial in the past, and unlike sequential encoding, it allows us to explicitly capture reentrant structures in the AMR graphs. We investigate the extent to which reentrancies (nodes with multiple parents) have an impact on AMR-to-text generation by comparing graph encoders to tree encoders, where reentrancies are not preserved. We show that improvements in the treatment of reentrancies and long-range dependencies contribute to higher overall scores for graph encoders. Our best model achieves 24.40 BLEU on LDC2015E86, outperforming the state of the art by 1.1 points and 24.54 BLEU on LDC2017T10, outperforming the state of the art by 1.24 points.