SAPG: Semantically-Aware Paraphrase Generation with AMR Graphs

Afonso Sousa, Henrique Cardoso

2025

Abstract

Automatically generating paraphrases is crucial for various natural language processing tasks. Current approaches primarily try to control the surface form of generated paraphrases by resorting to syntactic graph structures. However, paraphrase generation is rooted in semantics, but there are almost no works trying to leverage semantic structures as inductive biases for the task of generating paraphrases. We propose SAPG, a semantically-aware paraphrase generation model, which encodes Abstract Meaning Representation (AMR) graphs into a pretrained language model using a graph neural network-based encoder. We demonstrate that SAPG enables the generation of more diverse paraphrases by transforming the input AMR graphs, allowing for control over the output generations’ surface forms rooted in semantics. This approach ensures that the semantic meaning is preserved, offering flexibility in paraphrase generation without sacrificing fluency or coherence. Our extensive evaluation on two widely-used paraphrase generation datasets confirms the effectiveness of this method.

Download


Paper Citation


in Harvard Style

Sousa A. and Cardoso H. (2025). SAPG: Semantically-Aware Paraphrase Generation with AMR Graphs. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 861-871. DOI: 10.5220/0013379700003890


in Bibtex Style

@conference{icaart25,
author={Afonso Sousa and Henrique Cardoso},
title={SAPG: Semantically-Aware Paraphrase Generation with AMR Graphs},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={861-871},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013379700003890},
isbn={978-989-758-737-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - SAPG: Semantically-Aware Paraphrase Generation with AMR Graphs
SN - 978-989-758-737-5
AU - Sousa A.
AU - Cardoso H.
PY - 2025
SP - 861
EP - 871
DO - 10.5220/0013379700003890
PB - SciTePress