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.

翻译：基于翻译的AMR解析器因其简洁性和有效性近年来广受关注。这类解析器将线性化图结构预测为自由文本，从而避免了显式的结构建模。然而，这种简洁性忽略了AMR图中的结构局部性，并引入了表示共指关系所需的不必要标记。本文提出AMR解析的新目标形式及新型模型CHAP，该模型配备因果层次注意力与指针机制，能够将结构信息集成至Transformer解码器中。我们对多种替代建模方案进行了实证探究。实验表明，在无额外数据增强的设置下，我们的模型在五项基准测试中的四项上优于基线模型。