paper-with-me

Papers

Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation

2020-11-02 · COLING 2020 8 · Ruizhe Li, Xiao Li, Guanyi Chen, Chenghua Lin

The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling, where the approximate posterior collapses to the prior, and the model will totally ignore the latent variables and be degraded to a plain language model during text generation. Such an issue is particularly prevalent when RNN-based VAE models are employed for text modelling. In this paper, we propose a simple, generic architecture called Timestep-Wise Regularisation VAE (TWR-VAE), which can effectively avoid posterior collapse and can be applied to any RNN-based VAE models. The effectiveness and versatility of our model are demonstrated in different tasks, including language modelling and dialogue response generation.

📄 PDF Abstract BibTeX arXiv:2011.01136

Code (1)

ruizheliUOA/TWR-VAE 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingResponse GenerationText Generation

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음
USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

A Stable Variational Autoencoder for Text Modelling

2019-11-13 · WS 2019 10 · Ruizhe Li, Xiao Li, Chenghua Lin, Matthew Collinson 외

Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data. However, VAEs can suffer from an issue known as latent variable collapse (or KL loss vanishing), where the posteri…

Variational Autoencoders for Sparse and Overdispersed Discrete Data

2019-05-02 · He Zhao, Piyush Rai, Lan Du, Wray Buntine 외

Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data. Although probabilistic…

Collaborative FilteringMulti-Label LearningRecommendation Systems

Variational Autoencoders Without the Variation

2022-03-01 · Gregory A. Daly, Jonathan E. Fieldsend, Gavin Tabor

Variational autoencdoers (VAE) are a popular approach to generative modelling. However, exploiting the capabilities of VAEs in practice can be difficult. Recent work on regularised and entropic autoencoders have begun to…

Image Generation

Local Information Opponent Modelling Using Variational Autoencoders

2020-09-28 · Georgios Papoudakis, Filippos Christianos, Stefano V Albrecht

Modelling the behaviours of other agents (opponents) is essential for understanding how agents interact and making effective decisions. Existing methods for opponent modelling commonly assume knowledge of the local obser…

Deep Reinforcement Learning

Diffusion Priors In Variational Autoencoders

2021-06-29 · ICML Workshop INNF 2021 7 · Antoine Wehenkel, Gilles Louppe

Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and more outperformed by compet…

Denoising