AMR Parsing with Causal Hierarchical Attention and Pointers

2023/10/18 by Chao Lou, Kewei Tu, Lou, Chao +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2310.11964

openalex publication_date 2023/10/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• AMR Parsing as Sequence-to-Graph Transduction
• Levi Graph AMR Parser using Heterogeneous Attention
• Incorporating Graph Information in Transformer-based AMR Parsing
• Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing
• AMR Parsing with Action-Pointer Transformer