File:2017 UnsupervisedPretrainingforSeque Fig1.png
Jump to navigation
Jump to search
Size of this preview: 800 × 330 pixels. Other resolution: 1,011 × 417 pixels.
Original file (1,011 × 417 pixels, file size: 36 KB, MIME type: image/png)
Summary
Figure 1: Pretrained sequence to sequence model. The red parameters are the encoder and the blue parameters are the decoder. All parameters in a shaded box are pretrained, either from the source side (light red) or target side (light blue) language model. Otherwise, they are randomly initialized. In: Ramachandran et al. (2017).
File history
Click on a date/time to view the file as it appeared at that time.
Date/Time | Thumbnail | Dimensions | User | Comment | |
---|---|---|---|---|---|
current | 19:27, 3 March 2019 | 1,011 × 417 (36 KB) | Omoreira (talk | contribs) | Figure 1: Pretrained sequence to sequence model. The red parameters are the encoder and the blue parameters are the decoder. All parameters in a shaded box are pretrained, either from the source side (light... |
You cannot overwrite this file.
File usage
The following 5 pages use this file: