Commit
•
95ef0ae
1
Parent(s):
8aba977
Update README_English.md
Browse files- README_English.md +3 -3
README_English.md
CHANGED
|
@@ -29,12 +29,12 @@ onmt_translate -src input_text -model NOS-MT-en-gl -output ./output_file.txt -r
|
|
| 29 |
|
| 30 |
**Training**
|
| 31 |
|
| 32 |
-
In the training we have used authentic and synthetic corpora from [ProxectoNós](https://github.com/proxectonos/corpora). The former are corpora of translations directly produced by human translators. The latter are corpora of
|
| 33 |
|
| 34 |
**Training process**
|
| 35 |
|
| 36 |
+ Tokenization of the datasets made with linguakit tokeniser https://github.com/citiususc/Linguakit
|
| 37 |
-
+ The vocabulary for the models was generated through the script [learn_bpe.py](https://github.com/OpenNMT/OpenNMT-py/blob/master/tools/learn_bpe.py)
|
| 38 |
+ Using .yaml in this repository you can replicate the training process as follows
|
| 39 |
|
| 40 |
```bash
|
|
@@ -48,7 +48,7 @@ The parameters used for the development of the model can be directly consulted i
|
|
| 48 |
|
| 49 |
**Evaluation**
|
| 50 |
|
| 51 |
-
The BLEU evaluation of the models is made with a mixture of internally developed tests (gold1, gold2, test-suite)
|
| 52 |
|
| 53 |
| GOLD 1 | GOLD 2 | FLORES | TEST-SUITE|
|
| 54 |
| ------------- |:-------------:| -------:|----------:|
|
|
|
|
| 29 |
|
| 30 |
**Training**
|
| 31 |
|
| 32 |
+
In the training we have used authentic and synthetic corpora from [ProxectoNós](https://github.com/proxectonos/corpora). The former are corpora of translations directly produced by human translators. The latter are corpora of English-Portuguese translations, which we have converted into English-Galician by means of Portuguese-Galician translation with Opentrad/Apertium and transliteration for out-of-vocabulary words.
|
| 33 |
|
| 34 |
**Training process**
|
| 35 |
|
| 36 |
+ Tokenization of the datasets made with linguakit tokeniser https://github.com/citiususc/Linguakit
|
| 37 |
+
+ The vocabulary for the models was generated through the script [learn_bpe.py](https://github.com/OpenNMT/OpenNMT-py/blob/master/tools/learn_bpe.py) of OpenNMT
|
| 38 |
+ Using .yaml in this repository you can replicate the training process as follows
|
| 39 |
|
| 40 |
```bash
|
|
|
|
| 48 |
|
| 49 |
**Evaluation**
|
| 50 |
|
| 51 |
+
The BLEU evaluation of the models is made with a mixture of internally developed tests (gold1, gold2, test-suite) and other datasets available in Galician (Flores).
|
| 52 |
|
| 53 |
| GOLD 1 | GOLD 2 | FLORES | TEST-SUITE|
|
| 54 |
| ------------- |:-------------:| -------:|----------:|
|