VARIATIONAL AND HIERARCHICAL RECURRENT AUTOENCODER

檔案

本條目沒有附加檔案。

日期

2019-01-01

期刊名稱

2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)

卷期與頁次

頁 3202–3206

ISSN

1520-6149

ISBN

978-1-4799-8131-1

語言

英文

摘要

Despite a great success in learning representation for image data, it is challenging to learn the stochastic latent features from natural language based on variational inference. The difficulty in stochastic sequential learning is due to the posterior collapse caused by an autoregressive decoder which is prone to be too strong to learn sufficient latent information during optimization. To compensate this weakness in learning procedure, a sophisticated latent structure is required to assure good convergence so that random features are sufficiently captured for sequential decoding. This study presents a new variational recurrent autoencoder (VRAE) for sequence reconstruction. There are two complementary encoders consisting of a long short-term memory (LSTM) and a pyramid bidirectional LSTM which are merged to discover the global and local dependencies in a hierarchical latent variable model, respectively. Experiments on Penn Treebank and Yelp 2013 demonstrate that the proposed hierarchical VRAE is able to learn the complementary representation as well as tackle the posterior collapse in stochastic sequential learning. The performance of recurrent autoencoder is substantially improved in terms of perplexity.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Chien, J.-T., & Wang, C.-W. (2019). VARIATIONAL AND HIERARCHICAL RECURRENT AUTOENCODER. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 3202–3206. https://ir.lib.nycu.edu.tw/handle/11536/152927

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/152927