Generating Sentences from Disentangled Syntactic and Semantic Spaces
Full Text: P19-1602.pdfVariational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic information. In this paper, we propose to generate sentences from disentangled syntactic and semantic spaces. Our proposed method explicitly models syntactic information in the VAE’s latent space by using the linearized tree sequence, leading to better performance of language generation. Additionally, the advantage of sampling in the disentangled syntactic and semantic latent spaces enables us to perform novel applications, such as the unsupervised paraphrase generation and syntax transfer generation. Experimental results show that our proposed model achieves similar or better performance in various tasks, compared with state-of-the-art related work.
Citation
Y. Bao, H. Zhou, S. Huang, L. Li, L. Mou, O. Vechtomova, X. Dai, J. Chen. "Generating Sentences from Disentangled Syntactic and Semantic Spaces". International Conference on Computational Linguistics and the Association for Computational Linguist, pp 6008–6019, July 2019.Keywords: | |
Category: | In Conference |
Web Links: | DOI |
ACL |
BibTeX
@incollection{Bao+al:ACL19, author = {Yu Bao and Hao Zhou and Shujian Huang and Lei Li and Lili Mou and Olga Vechtomova and Xin-yu Dai and Jiajun Chen}, title = {Generating Sentences from Disentangled Syntactic and Semantic Spaces}, Pages = {6008–6019}, booktitle = {International Conference on Computational Linguistics and the Association for Computational Linguist}, year = 2019, }Last Updated: February 02, 2021
Submitted by Sabina P