wjbmattingly
commited on
Commit
•
413e21c
1
Parent(s):
9a75faf
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,70 @@
|
|
1 |
-
---
|
2 |
-
license:
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- multilingual
|
5 |
+
library_name: gliner
|
6 |
+
datasets:
|
7 |
+
- medieval-data/medieval-latin-ner-HOME-Alcar-sents
|
8 |
+
pipeline_tag: token-classification
|
9 |
+
---
|
10 |
+
|
11 |
+
# About
|
12 |
+
|
13 |
+
This is a GLiNER model finetuned on medieval Latin. It was trained to improve the identification of PERSON and LOC. It was finetuned from [urchade/gliner_multi-v2.1](https://huggingface.co/urchade/gliner_multi-v2.1). The model was finetuned on 1,500 annotations from the [Home Alcar sentences](https://huggingface.co/datasets/medieval-data/medieval-latin-ner-HOME-Alcar-sents). Only 1,500 were selected to prevent catastrophic forgetting.
|
14 |
+
|
15 |
+
GLiNER is a Named Entity Recognition (NER) model capable of identifying any entity type using a bidirectional transformer encoder (BERT-like). It provides a practical alternative to traditional NER models, which are limited to predefined entities, and Large Language Models (LLMs) that, despite their flexibility, are costly and large for resource-constrained scenarios.
|
16 |
+
|
17 |
+
## Installation
|
18 |
+
To use this model, you must install the GLiNER Python library:
|
19 |
+
```
|
20 |
+
!pip install gliner
|
21 |
+
```
|
22 |
+
|
23 |
+
## Usage
|
24 |
+
Once you've downloaded the GLiNER library, you can import the GLiNER class. You can then load this model using `GLiNER.from_pretrained` and predict entities with `predict_entities`.
|
25 |
+
|
26 |
+
```python
|
27 |
+
from gliner import GLiNER
|
28 |
+
|
29 |
+
model = GLiNER.from_pretrained("medieval-data/gliner_multi-v2.1-medieval-latin")
|
30 |
+
|
31 |
+
text = """
|
32 |
+
Testes : magister Stephanus cantor Autissiodorensis , Petrus capellanus comitis , Gaufridus clericus , Hugo de Argenteolo , Milo Filluns , Johannes Maleherbe , Nivardus de Argenteolo , Columbus tunc prepositus Tornodorensis , Johannes prepositus Autissiodorensis , Johannes Brisebarra .
|
33 |
+
"""
|
34 |
+
|
35 |
+
labels = ["PERSON", "LOC"]
|
36 |
+
|
37 |
+
entities = model.predict_entities(text, labels)
|
38 |
+
|
39 |
+
for entity in entities:
|
40 |
+
print(entity["text"], "=>", entity["label"])
|
41 |
+
```
|
42 |
+
|
43 |
+
```
|
44 |
+
Stephanus => PERSON
|
45 |
+
Autissiodorensis => LOC
|
46 |
+
Petrus => PERSON
|
47 |
+
Gaufridus => PERSON
|
48 |
+
Hugo de Argenteolo => PERSON
|
49 |
+
Milo Filluns => PERSON
|
50 |
+
Johannes Maleherbe => PERSON
|
51 |
+
Nivardus de Argenteolo => PERSON
|
52 |
+
Columbus => PERSON
|
53 |
+
Tornodorensis => LOC
|
54 |
+
Johannes => PERSON
|
55 |
+
Autissiodorensis => LOC
|
56 |
+
Johannes Brisebarra => PERSON
|
57 |
+
```
|
58 |
+
|
59 |
+
|
60 |
+
## Citation to Original GLiNER Model
|
61 |
+
```bibtex
|
62 |
+
@misc{zaratiana2023gliner,
|
63 |
+
title={GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer},
|
64 |
+
author={Urchade Zaratiana and Nadi Tomeh and Pierre Holat and Thierry Charnois},
|
65 |
+
year={2023},
|
66 |
+
eprint={2311.08526},
|
67 |
+
archivePrefix={arXiv},
|
68 |
+
primaryClass={cs.CL}
|
69 |
+
}
|
70 |
+
```
|