https://scholars.lib.ntu.edu.tw/handle/123456789/632855
標題: | Conditional Sentence Rephrasing without Parallel Training Corpus | 作者: | Lee, Yen Ting Li, Cheng Te SHOU-DE LIN |
公開日期: | 1-一月-2022 | 來源出版物: | ICMEW 2022 - IEEE International Conference on Multimedia and Expo Workshops 2022, Proceedings | 摘要: | This paper aims to rephrase a sentence with a given condition, and the generated sentence should be similar to the origin sentence and satisfy the given condition without parallel training corpus. We propose a conditional sentence VAE (CS-VAE) model to solve the task. CS-VAE is trained as an autoencoder, along with the condition control on the generated sentence with the same semantics. With the experimental demonstration supported, CS-VAE is proven to effectively solve the task with high-quality sentences. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/632855 | ISBN: | 9781665472180 | DOI: | 10.1109/ICMEW56448.2022.9859385 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。