CASIA OpenIR  > 自然语言处理团队
Sequence Generation: From Both Sides to the Middle
Long Zhou; Jiajun Zhang; Chengqing Zong; Heng Yu
Conference NameIJCAI-2019
Conference Date2019
Conference PlaceMacau, China

The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization. Such a framework usually generates a sequence token by token from left to right, hence (1) this autoregressive decoding procedure is time-consuming when the output sentence becomes longer, and (2) it lacks the guidance of future context which is crucial to avoid under-translation. To alleviate these issues, we propose a synchronous bidirectional sequence generation (SBSG) model which predicts its outputs from both sides to the middle simultaneously. In the SBSG model, we enable the left-to-right (L2R) and right-to-left (R2L) generation to help and interact with each other by leveraging interactive bidirectional attention network. Experiments on neural machine translation (En⇒De, Ch⇒En, and En⇒Ro) and text summarization tasks show that the proposed model significantly speeds up decoding while improving the generation quality compared to the autoregressive Transformer.

Document Type会议论文
Recommended Citation
GB/T 7714
Long Zhou,Jiajun Zhang,Chengqing Zong,et al. Sequence Generation: From Both Sides to the Middle[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
0760.pdf(738KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Long Zhou]'s Articles
[Jiajun Zhang]'s Articles
[Chengqing Zong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Long Zhou]'s Articles
[Jiajun Zhang]'s Articles
[Chengqing Zong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Long Zhou]'s Articles
[Jiajun Zhang]'s Articles
[Chengqing Zong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 0760.pdf
Format: Adobe PDF
All comments (0)
No comment.

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