SAPG: Semantically-Aware Paraphrase Generation with AMR Graphs

• Type: Article in International Conference Proceedings Book
• Date: 2025

Authors

Sousa, A (Author) Other; Henrique Lopes Cardoso (Author) FEUP

Conference proceedings International

Title: Proceedings of the 17th International Conference on Agents and Artificial Intelligence, ICAART 2025 - Volume 2, Porto, Portugal, February 23-25, 2025.

Pages: 861-871

17th International Conference on Agents and Artificial Intelligence, ICAART 2025

Porto, 23 February 2025 through 25 February 2025

Indexing

Scopus - 0 Citations

Other information

Authenticus ID: P-018-HHN

DOI: 10.5220/0013379700003890

Abstract (EN): 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. © 2025 by SCITEPRESS ¿ Science and Technology Publications, Lda.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 10