paper-with-me

Papers

Topic-Guided Variational Auto-Encoder for Text Generation

2019-06-01 · NAACL 2019 6 · Wenlin Wang, Zhe Gan, Hongteng Xu, Ruiyi Zhang, Guoyin Wang, Dinghan Shen, Changyou Chen, Lawrence Carin

We propose a topic-guided variational auto-encoder (TGVAE) model for text generation. Distinct from existing variational auto-encoder (VAE) based approaches, which assume a simple Gaussian prior for latent code, our model specifies the prior as a Gaussian mixture model (GMM) parametrized by a neural topic module. Each mixture component corresponds to a latent topic, which provides a guidance to generate sentences under the topic. The neural topic module and the VAE-based neural sequence module in our model are learned jointly. In particular, a sequence of invertible Householder transformations is applied to endow the approximate posterior of the latent code with high flexibility during the model inference. Experimental results show that our TGVAE outperforms its competitors on both unconditional and conditional text generation, which can also generate semantically-meaningful sentences with various topics.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Conditional Text GenerationText Generation

Similar Papers 제목 키워드 기반

Topic-Guided Variational Autoencoders for Text Generation

2019-03-17 · Wenlin Wang, Zhe Gan, Hongteng Xu, Ruiyi Zhang 외

We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our mo…

Conditional Text GenerationText Generation

Dirichlet Variational Autoencoder for Text Modeling

2018-10-31 · Yijun Xiao, Tiancheng Zhao, William Yang Wang

We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at r…

Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation

2023-12-15 · Youngjoon Yoo, Jongwon Choi

This paper introduces a novel approach for topic modeling utilizing latent codebooks from Vector-Quantized Variational Auto-Encoder~(VQ-VAE), discretely encapsulating the rich information of the pre-trained embeddings su…

Image GenerationLanguage ModelingLanguage Modelling

Variational Gaussian Topic Model with Invertible Neural Projections

2021-05-21 · Rui Wang, Deyu Zhou, Yuxuan Xiong, Haiping Huang

Neural topic models have triggered a surge of interest in extracting topics from text automatically since they avoid the sophisticated derivations in conventional topic models. However, scarce neural topic models incorpo…

DecoderTopic ModelsWord Embeddings

Inductive Topic Variational Graph Auto-Encoder for Text Classification

2021-06-01 · NAACL 2021 4 · Qianqian Xie, Jimin Huang, Pan Du, Min Peng 외

Graph convolutional networks (GCNs) have been applied recently to text classification and produced an excellent performance. However, existing GCN-based methods do not assume an explicit latent semantic structure of docu…

ClassificationInductive LearningRepresentation LearningSemi-Supervised Text Classification+2