AMR Parsing with Causal Hierarchical Attention and Pointers
This work improves AMR parsing for natural language processing applications, representing an incremental advance over existing translation-based methods.
The paper tackled the problem of AMR parsing by addressing the neglect of structural locality and unnecessary tokens in translation-based parsers, introducing a new model CHAP that integrates structures into the Transformer decoder, resulting in outperforming baseline models on four out of five benchmarks without additional data.
Translation-based AMR parsers have recently gained popularity due to their simplicity and effectiveness. They predict linearized graphs as free texts, avoiding explicit structure modeling. However, this simplicity neglects structural locality in AMR graphs and introduces unnecessary tokens to represent coreferences. In this paper, we introduce new target forms of AMR parsing and a novel model, CHAP, which is equipped with causal hierarchical attention and the pointer mechanism, enabling the integration of structures into the Transformer decoder. We empirically explore various alternative modeling options. Experiments show that our model outperforms baseline models on four out of five benchmarks in the setting of no additional data.