Generative adversarial training for neural machine translation.
Neurocomputing(2018)
Abstract
•The traditional neural machine translation is typically optimized with human-designed approximate loss function.•The proposed method trains the neural machine translation model to generate human-like translations directly.•The single generator-discriminator net is extended into the multi adversarial net which contains multiple generators and discriminators.•The proposed models achieve significant improvements.
MoreTranslated text
Key words
Neural machine translation,Multi generative adversarial net,Human-like translation
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined