AMR-TST: Abstract meaning representation-based text style transfer

Kaize SHI, Xueyao SUN, Li HE, Dingxian WANG, Qing LI, Guandong XU

Research output: Chapter in Book/Report/Conference proceedingChapters

1 Citation (Scopus)

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 ex-plainability 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. Copyright © 2023 Association for Computational Linguistics.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics: ACL 2023
Place of PublicationCanada
PublisherAssociation for Computational Linguistics (ACL)
Pages4231-4243
ISBN (Electronic)9781959429623
DOIs
Publication statusPublished - 2023

Citation

Shi, K., Sun, X., He, L., Wang, D., Li, Q., & Xu, G. (2023). AMR-TST: Abstract meaning representation-based text style transfer. In Findings of the Association for Computational Linguistics: ACL 2023 (pp. 4231-4243). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-acl.260

Fingerprint

Dive into the research topics of 'AMR-TST: Abstract meaning representation-based text style transfer'. Together they form a unique fingerprint.