AMR-TST: Abstract Meaning Representation-based Text Style Transfer
Paper
| Paper/Presentation Title | AMR-TST: Abstract Meaning Representation-based Text Style Transfer |
|---|---|
| Presentation Type | Paper |
| Authors | Shi, Kaize, Sun, Xueyao, He, Li, Wang, Dingxian, Li, Qing and Xu, Guandong |
| Journal Citation | pp. 4231-4243 |
| Number of Pages | 13 |
| Year | 2023 |
| Place of Publication | Canada |
| Web Address (URL) of Paper | https://aclanthology.org/2023.findings-acl.260/ |
| Web Address (URL) of Conference Proceedings | https://aclanthology.org/volumes/2023.findings-acl/ |
| Conference/Event | Findings of the Association for Computational Linguistics: ACL 2023 |
| Event Details | Findings of the Association for Computational Linguistics: ACL 2023 Delivery In person Event Date 09 to end of 14 Jul 2023 Event Location Toronto, Canada Event Web Address (URL) |
| 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. |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 4602. Artificial intelligence |
| Byline Affiliations | University of Technology Sydney |
| Hong Kong Polytechnic University, China |
https://research.usq.edu.au/item/10097y/amr-tst-abstract-meaning-representation-based-text-style-transfer
Download files
15
total views3
total downloads7
views this month2
downloads this month