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

Jeongwoo Kang, Maximin Coavoux, Cédric Lopez, Didier Schwab
5/13/2025
cs.CL

No official code found. Best implementation: Emvista/Triple_AMR_Parser (1 star, last commit 2025-03-21).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

Emvista/Triple_AMR_ParserCommunity100%
10Shell, PythonNov 4, 20241 years ago

Similar Papers

Graph Linearization Methods for Reasoning on Graphs with Large Language Models

81% match2024

SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generation

79% match2025

Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM

79% match1 repo12024

Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs

79% match2025

On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL

77% match2024

Dependency Graph Parsing as Sequence Labeling

77% match2024

Cite this paper

@article{kang2025reassessing,
  title  = {Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding},
  author = {Jeongwoo Kang and Maximin Coavoux and Cédric Lopez and Didier Schwab},
  year   = {2025},
  eprint = {2505.08504},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.08504v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.08504.svg)](https://codeofpaper.com/paper/2505.08504)

Discussion