Levi Graph AMR Parser using Heterogeneous Attention

ACL (IWPT) 2021  ·  Han He, Jinho D. Choi ·

Coupled with biaffine decoders, transformers have been effectively adapted to text-to-graph transduction and achieved state-of-the-art performance on AMR parsing. Many prior works, however, rely on the biaffine decoder for either or both arc and label predictions although most features used by the decoder may be learned by the transformer already. This paper presents a novel approach to AMR parsing by combining heterogeneous data (tokens, concepts, labels) as one input to a transformer to learn attention, and use only attention matrices from the transformer to predict all elements in AMR graphs (concepts, arcs, labels). Although our models use significantly fewer parameters than the previous state-of-the-art graph parser, they show similar or better accuracy on AMR 2.0 and 3.0.

PDF Abstract ACL (IWPT) 2021 PDF ACL (IWPT) 2021 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
AMR Parsing LDC2017T10 ND+AD+LV Smatch 80 # 14


No methods listed for this paper. Add relevant methods here