Generating Sentences from Disentangled Syntactic and Semantic Spaces
Citations Over TimeTop 10% of 2019 papers
Abstract
Variational 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 syntaxtransfer generation. Experimental results show that our proposed model achieves similar or better performance in various tasks, compared with state-of-the-art related work.
Related Papers
- → Constructing Corpora for the Development and Evaluation of Paraphrase Systems(2008)85 cited
- → PKU Paraphrase Bank: A Sentence-Level Paraphrase Corpus for Chinese(2019)10 cited
- → APEM: Automatic paraphrase evaluation using morphological analysis for the Korean language(2016)1 cited
- → Degarbayan-SC: A Colloquial Paraphrase Farsi Subtitles Dataset(2022)
- → ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation(2023)