Commit
·
08aadb6
1
Parent(s):
5c3a2a2
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,4 +18,16 @@ This repo contains the model and the notebook [to this Keras example on Characte
|
|
| 18 |
Full credits to: [fchollet](https://twitter.com/fchollet)
|
| 19 |
|
| 20 |
## Background Information
|
| 21 |
-
This example demonstrates how to implement a basic character-level recurrent sequence-to-sequence model. We apply it to translating short English sentences into short French sentences, character-by-character. Note that it is fairly unusual to do character-level machine translation, as word-level models are more common in this domain.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
Full credits to: [fchollet](https://twitter.com/fchollet)
|
| 19 |
|
| 20 |
## Background Information
|
| 21 |
+
This example demonstrates how to implement a basic character-level recurrent sequence-to-sequence model. We apply it to translating short English sentences into short French sentences, character-by-character. Note that it is fairly unusual to do character-level machine translation, as word-level models are more common in this domain.
|
| 22 |
+
|
| 23 |
+
## Limitations
|
| 24 |
+
It works on text of length <= 15 characters
|
| 25 |
+
|
| 26 |
+
## Parameters needed for using the model
|
| 27 |
+
```python
|
| 28 |
+
latent_dim = 256
|
| 29 |
+
num_encoder_tokens = 71
|
| 30 |
+
max_encoder_seq_length = 15
|
| 31 |
+
num_decoder_tokens = 92
|
| 32 |
+
max_decoder_seq_length = 59
|
| 33 |
+
```
|