AMR-TST: Abstract Meaning Representation-based Text Style Transfer
Kaize Shi, Xueyao Sun, Li He, Dingxian Wang, Qing Li, Guandong Xu
Abstract
Abstract Meaning Representation (AMR) is a semantic representation that can enhance natural language generation (NLG) by providing a logical semantic input. In this paper, we propose the AMR-TST, an AMR-based text style transfer (TST) technique. The AMR-TST converts the source text to an AMR graph and generates the transferred text based on the AMR graph modified by a TST policy named style rewriting. Our method combines both the explainability and diversity of explicit and implicit TST methods. The experiments show that the proposed method achieves state-of-the-art results compared with other baseline models in automatic and human evaluations. The generated transferred text in qualitative evaluation proves the AMR-TST have significant advantages in keeping semantic features and reducing hallucinations. To the best of our knowledge, this work is the first to apply the AMR method focusing on node-level features to the TST task.
BibTeX
@inproceedings{shi-etal-2023-amr,
title = "{AMR}-{TST}: {A}bstract {M}eaning {R}epresentation-based Text Style Transfer",
author = "Shi, Kaize and
Sun, Xueyao and
He, Li and
Wang, Dingxian and
Li, Qing and
Xu, Guandong",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.260/",
doi = "10.18653/v1/2023.findings-acl.260",
pages = "4231--4243"
}