Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,49 @@
|
|
1 |
-
---
|
2 |
-
language:
|
3 |
-
- multilingual
|
4 |
-
- pl
|
5 |
-
- ru
|
6 |
-
- uk
|
7 |
-
- bg
|
8 |
-
- cs
|
9 |
-
- sl
|
10 |
-
datasets:
|
11 |
-
- SlavicNER
|
12 |
-
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- multilingual
|
4 |
+
- pl
|
5 |
+
- ru
|
6 |
+
- uk
|
7 |
+
- bg
|
8 |
+
- cs
|
9 |
+
- sl
|
10 |
+
datasets:
|
11 |
+
- SlavicNER
|
12 |
+
license: apache-2.0
|
13 |
+
library_name: transformers
|
14 |
+
pipeline_tag: text2text-generation
|
15 |
+
tags:
|
16 |
+
- entity linking
|
17 |
+
widget:
|
18 |
+
- text: "pl:Polsce"
|
19 |
+
- text: "cs:Velké Británii"
|
20 |
+
- text: "bg:българите"
|
21 |
+
- text: "ru:Великобританию"
|
22 |
+
- text: "sl:evropske komisije"
|
23 |
+
- text: "uk:Європейського агентства лікарських засобів"
|
24 |
+
---
|
25 |
+
|
26 |
+
# Model description
|
27 |
+
|
28 |
+
This is a baseline model for named entity **lemmatization** trained on the single-out topic split of the
|
29 |
+
[SlavicNER corpus](https://github.com/SlavicNLP/SlavicNER).
|
30 |
+
|
31 |
+
|
32 |
+
# Usage
|
33 |
+
|
34 |
+
You can use this model directly with a pipeline for text2text generation:
|
35 |
+
|
36 |
+
```python
|
37 |
+
from transformers import pipeline
|
38 |
+
|
39 |
+
model_name = "SlavicNLP/slavicner-linking-single-out-large"
|
40 |
+
pipe = pipeline("text2text-generation", model_name)
|
41 |
+
|
42 |
+
texts = ["pl:Polsce", "cs:Velké Británii", "bg:българите", "ru:Великобританию", "sl:evropske komisije",
|
43 |
+
"uk:Європейського агентства лікарських засобів"]
|
44 |
+
|
45 |
+
outputs = pipe(texts)
|
46 |
+
|
47 |
+
ids = [o['generated_text'] for o in outputs]
|
48 |
+
print(ids)
|
49 |
+
# ['GPE-Poland', 'GPE-Great-Britain', 'GPE-Bulgaria', 'GPE-Great-Britain', 'ORG-European-Commission', 'ORG-EMA-European-Medicines-Agency']
|