https://scholars.lib.ntu.edu.tw/handle/123456789/631967
標題: | Adversarial Rap Lyric Generation | 作者: | Chuang, Yun Yen Hsu, Hung Min RAY-I CHANG HUNG-YI LEE |
關鍵字: | Generative Adversarial Network | Language generation | Machine Learning | Rap Lyric | 公開日期: | 1-一月-2022 | 來源出版物: | Proceedings - 2022 4th International Conference on Natural Language Processing, ICNLP 2022 | 摘要: | In this paper, we design a novel text generation method called RapGAN for RLG (Rap Lyric Generation). RapGAN proposes two new schemes, PRO (Phrase Roll-Out) and AREGS (Attention Reward at Every Generation Step), to achieve efficient and effective RLG. The conventional text generation methods need to complete the entire-generated sentence in GAN (Generative Adversarial Network) training. RapGAN uses PRO as selective attention to reward only meaningful phrases in every generation step. Due to the varying length of phrases segmented by PRO, we employ an attention-based neural network that can capture the local feature of phrases and the semantics of global sentences as our discriminator. Therefore, we propose AREGS that reward the alignment weights of the attention-based discriminator with feature matching. Our method can provide different weights on different words to improve RLG's diversity, originality and fluency. Experimental results s how that our RapGAN outperforms the state-of-the-art RLG methods on many essential metrics of text generation. We also show the human evaluation to illustrate the relations between human perception and typical NLP metrics in diversity, originality and fluency. Our proposed method can facilitate real-world applications in content open RLG dataset in this paper. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/631967 | ISBN: | 9781665495448 | DOI: | 10.1109/ICNLP55136.2022.00077 |
顯示於: | 工程科學及海洋工程學系 |
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。