VARIATIONAL AND HIERARCHICAL RECURRENT AUTOENCODER
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
3206 | en_US |
dc.citation.spage |
3202 | en_US |
dc.citation.woscount |
1 | en_US |
dc.contributor.author |
Chien, Jen-Tzung | en_US |
dc.contributor.author |
Wang, Chun-Wei | en_US |
dc.contributor.department |
電機工程學系 | zh_TW |
dc.contributor.department |
Department of Electrical and Computer Engineering | en_US |
dc.date.accessioned |
2019-10-05T00:09:44Z | |
dc.date.available |
2019-10-05T00:09:44Z | |
dc.date.issued |
2019-01-01 | en_US |
dc.description.abstract |
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. | en_US |
dc.identifier.isbn |
978-1-4799-8131-1 | en_US |
dc.identifier.issn |
1520-6149 | en_US |
dc.identifier.journal |
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/152927 | |
dc.identifier.wosnumber |
WOS:000482554003085 | en_US |
dc.language.iso |
en_US | en_US |
dc.subject |
Sequence generation | en_US |
dc.subject |
recurrent neural network | en_US |
dc.subject |
variational autoencoder | en_US |
dc.subject |
hierarchical model | en_US |
dc.title |
VARIATIONAL AND HIERARCHICAL RECURRENT AUTOENCODER | en_US |
dc.type |
Proceedings Paper | en_US |
檔案
本條目沒有附加檔案。
所屬典藏: 會議論文
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
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