AMR Parsing with Causal Hierarchical Attention and Pointers
Submission Type: Regular Long Paper
Submission Track: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.
Keywords: semantic parsing, AMR parsing, hierarical attention, pointer mechanism
Abstract: 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.
Submission Number: 4994
Loading