Communication Dans Un Congrès Année : 2025

Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding

Résumé

Sequence-to-sequence models are widely used to train Abstract Meaning Representation (Banarescu et al., 2013, AMR) parsers. To train such models, AMR graphs have to be linearized into a one-line text format. While Penman encoding is typically used for this purpose, we argue that it has limitations: (1) for deep graphs, some closely related nodes are located far apart in the linearized text (2) Penman's tree-based encoding necessitates inverse roles to handle node re-entrancy, doubling the number of relation types to predict. To address these issues, we propose a triple-based linearization method and compare its efficiency with Penman linearization. Although triples are well suited to represent a graph, our results suggest room for improvement in triple encoding to better compete with Penman's concise and explicit representation of a nested graph structure.

Fichier principal
Vignette du fichier
insights_2025.pdf (475.1 Ko) Télécharger le fichier

Dates et versions

hal-05066146 , version 1 (13-05-2025)

Licence

Identifiants

Citer

Jeongwoo Kang, Maximin Coavoux, Cédric Lopez, Didier Schwab. Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding. 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (Insights 2025), May 2025, Albuquerque, NM, United States. pp.15-23, ⟨10.18653/v1/2025.insights-1.3⟩. ⟨hal-05066146⟩
120 Consultations
92 Téléchargements

Altmetric

Partager

  • More