Update README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
### opus-mt-NORTH_EU-NORTH_EU
|
| 2 |
+
|
| 3 |
+
* source languages: de,nl,fy,af,da,fo,is,no,nb,nn,sv
|
| 4 |
+
* target languages: de,nl,fy,af,da,fo,is,no,nb,nn,sv
|
| 5 |
+
* OPUS readme: [de+nl+fy+af+da+fo+is+no+nb+nn+sv-de+nl+fy+af+da+fo+is+no+nb+nn+sv](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de+nl+fy+af+da+fo+is+no+nb+nn+sv-de+nl+fy+af+da+fo+is+no+nb+nn+sv/README.md)
|
| 6 |
+
|
| 7 |
+
* dataset: opus
|
| 8 |
+
* model: transformer-align
|
| 9 |
+
* pre-processing: normalization + SentencePiece
|
| 10 |
+
* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
|
| 11 |
+
* download original weights: [opus-2020-01-15.zip](https://object.pouta.csc.fi/OPUS-MT-models/de+nl+fy+af+da+fo+is+no+nb+nn+sv-de+nl+fy+af+da+fo+is+no+nb+nn+sv/opus-2020-01-15.zip)
|
| 12 |
+
* test set translations: [opus-2020-01-15.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de+nl+fy+af+da+fo+is+no+nb+nn+sv-de+nl+fy+af+da+fo+is+no+nb+nn+sv/opus-2020-01-15.test.txt)
|
| 13 |
+
* test set scores: [opus-2020-01-15.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de+nl+fy+af+da+fo+is+no+nb+nn+sv-de+nl+fy+af+da+fo+is+no+nb+nn+sv/opus-2020-01-15.eval.txt)
|
| 14 |
+
|
| 15 |
+
## Benchmarks
|
| 16 |
+
|
| 17 |
+
| testset | BLEU | chr-F |
|
| 18 |
+
|-----------------------|-------|-------|
|
| 19 |
+
| Tatoeba.de.sv | 48.1 | 0.663 |
|
| 20 |
+
|