UM
Latent Attribute Based Hierarchical Decoder for Neural Machine Translation
Liu,Xuebo1; Wong,Derek F.1; Chao,Lidia S.1; Liu,Yang2
2019-12-01
Source PublicationIEEE/ACM Transactions on Audio Speech and Language Processing
ISSN2329-9290
Volume27Issue:12Pages:2103-2112
AbstractNeural machine translation (NMT) has achieved state-of-the-art performance in many translation tasks. However, because the computational cost increases with the size of the search space for predicting the target words, the translation quality of NMT is constrained by the limited vocabulary. To alleviate this problem, we propose a novel dynamic hierarchical decoder for NMT to utilize all of the target words in the training and decoding process. In the proposed model, a target word is represented by two latent attribute vectors rather than a word vector. The model is trained to dynamically put together those words that share similar linguistic attributes. The prediction of a target word is, therefore, turned into the prediction of attribute vectors, where the softmax functions are performed at the attribute level. This greatly reduces the model size and the decoding time. Our experimental results demonstrate that the proposed model significantly outperforms the NMT baselines in both Chinese-English and English-German translation tasks.
Keywordhierarchical decoder Latent attribute limited vocabulary neural machine translation (NMT)
DOI10.1109/TASLP.2019.2941587
URLView the original
Language英語English
Scopus ID2-s2.0-85073061579
Fulltext Access
Citation statistics
Cited Times [WOS]:5   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionUniversity of Macau
Corresponding AuthorWong,Derek F.
Affiliation1.Natural Language Processing and Portuguese-Chinese Machine Translation (NLP2CT) Laboratory,University of Macau,Macao
2.Department of Computer Science and Technology,Tsinghua University,Beijing,100084,China
First Author AffilicationUniversity of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Liu,Xuebo,Wong,Derek F.,Chao,Lidia S.,et al. Latent Attribute Based Hierarchical Decoder for Neural Machine Translation[J]. IEEE/ACM Transactions on Audio Speech and Language Processing,2019,27(12):2103-2112.
APA Liu,Xuebo,Wong,Derek F.,Chao,Lidia S.,&Liu,Yang.(2019).Latent Attribute Based Hierarchical Decoder for Neural Machine Translation.IEEE/ACM Transactions on Audio Speech and Language Processing,27(12),2103-2112.
MLA Liu,Xuebo,et al."Latent Attribute Based Hierarchical Decoder for Neural Machine Translation".IEEE/ACM Transactions on Audio Speech and Language Processing 27.12(2019):2103-2112.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu,Xuebo]'s Articles
[Wong,Derek F.]'s Articles
[Chao,Lidia S.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu,Xuebo]'s Articles
[Wong,Derek F.]'s Articles
[Chao,Lidia S.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu,Xuebo]'s Articles
[Wong,Derek F.]'s Articles
[Chao,Lidia S.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.