Commit
β’
3e8baa2
1
Parent(s):
2374e1d
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- universal_dependencies
|
4 |
+
language:
|
5 |
+
- tl
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
pipeline_tag: token-classification
|
9 |
+
---
|
10 |
+
|
11 |
+
## Model Specification
|
12 |
+
- Model: XLM-RoBERTa (base-sized model)
|
13 |
+
- Training Data:
|
14 |
+
- Combined Afrikaans, Hebrew, Bulgarian, Vietnamese, Norwegian, Urdu, & Czech corpora (Top 7 Languages)
|
15 |
+
- Training Details:
|
16 |
+
- Base configurations with learning rate 5e-5
|
17 |
+
## Evaluation
|
18 |
+
- Evaluation Dataset: Universal Dependencies Tagalog Ugnayan (Testing Set)
|
19 |
+
- Tested in a zero-shot cross-lingual scenario on a Universal Dependencies Tagalog Ugnayan testing dataset (with 75.18\% Accuracy)
|
20 |
+
## POS Tags
|
21 |
+
- ADJ β ADP β ADV β CCONJ β DET β INTJ β NOUN β NUM β PART β PRON β PROPN β PUNCT β SCONJ β VERB
|