Incorporating Discriminator in Sentence Generation: a Gibbs Sampling Method
arXiv:1802.08970
Abstract
Generating plausible and fluent sentence with desired properties has long been a challenge. Most of the recent works use recurrent neural networks (RNNs) and their variants to predict following words given previous sequence and target label. In this paper, we propose a novel framework to generate constrained sentences via Gibbs Sampling. The candidate sentences are revised and updated iteratively, with sampled new words replacing old ones. Our experiments show the effectiveness of the proposed method to generate plausible and diverse sentences.
arXiv commentpublished in The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 2018
References in corpus (7)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Toward Controlled Generation of Text
- Language as a Latent Variable: Discrete Generative Models for Sentence Compression
- Nonparametric Variational Auto-encoders for Hierarchical Representation Learning
- Generating Sentences by Editing Prototypes
- Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation