File:UNSUPERMONO-Fig2.png
Original file (1,007 × 445 pixels, file size: 92 KB, MIME type: image/png)
Illustration of the proposed architecture and training objectives. The architecture is a sequence to sequence model, with both encoder and decoder operating on two languages depending on an input language identifier that swaps lookup tables. Top (auto-encoding): the model learns to denoise sentences in each domain. Bottom (translation): like before, except that we encode from another language, using as input the translation produced by the model at the previous iteration (light blue box). The green ellipses indicate terms in the loss function.
File history
Click on a date/time to view the file as it appeared at that time.
Date/Time | Thumbnail | Dimensions | User | Comment | |
---|---|---|---|---|---|
current | 17:47, 11 August 2020 | 1,007 × 445 (92 KB) | Abdelrhman.d (talk | contribs) |
You cannot overwrite this file.
File usage
The following page uses this file: