Token Classification
GLiNER
PyTorch
English
Files changed (1) hide show
  1. README.md +77 -2
README.md CHANGED
@@ -1,6 +1,81 @@
1
  ---
2
  license: apache-2.0
3
  language:
4
- - en
5
  pipeline_tag: token-classification
6
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  language:
4
+ - en
5
  pipeline_tag: token-classification
6
+ ---
7
+
8
+ # Model Card for GLiNER-base
9
+
10
+ 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.
11
+
12
+ ## Links
13
+
14
+ * Paper: https://arxiv.org/abs/2311.08526
15
+ * Repository: https://github.com/urchade/GLiNER
16
+
17
+ ## Installation
18
+ To use this model, you must download the GLiNER repository and install its dependencies:
19
+ ```
20
+ !git clone https://github.com/urchade/GLiNER.git
21
+ %cd GLiNER
22
+ !pip install -r requirements.txt
23
+ ```
24
+
25
+ ## Usage
26
+ Once you've downloaded the GLiNER repository, you can import the GLiNER class from the `model` file. You can then load this model using `GLiNER.from_pretrained` and predict entities with `predict_entities`.
27
+
28
+ ```python
29
+ from model import GLiNER
30
+
31
+ model = GLiNER.from_pretrained("urchade/gliner_base")
32
+
33
+ text = """
34
+ Cristiano Ronaldo dos Santos Aveiro (Portuguese pronunciation: [kɾiʃˈtjɐnu ʁɔˈnaldu]; born 5 February 1985) is a Portuguese professional footballer who plays as a forward for and captains both Saudi Pro League club Al Nassr and the Portugal national team. Widely regarded as one of the greatest players of all time, Ronaldo has won five Ballon d'Or awards,[note 3] a record three UEFA Men's Player of the Year Awards, and four European Golden Shoes, the most by a European player. He has won 33 trophies in his career, including seven league titles, five UEFA Champions Leagues, the UEFA European Championship and the UEFA Nations League. Ronaldo holds the records for most appearances (183), goals (140) and assists (42) in the Champions League, goals in the European Championship (14), international goals (128) and international appearances (205). He is one of the few players to have made over 1,200 professional career appearances, the most by an outfield player, and has scored over 850 official senior career goals for club and country, making him the top goalscorer of all time.
35
+ """
36
+
37
+ labels = ["person", "award", "date", "competitions", "teams"]
38
+
39
+ entities = model.predict_entities(text, labels)
40
+
41
+ for entity in entities:
42
+ print(entity["text"], "=>", entity["label"])
43
+ ```
44
+
45
+ ```
46
+ Cristiano Ronaldo dos Santos Aveiro => person
47
+ 5 February 1985 => date
48
+ Al Nassr => teams
49
+ Portugal national team => teams
50
+ Ballon d'Or => award
51
+ UEFA Men's Player of the Year Awards => award
52
+ European Golden Shoes => award
53
+ UEFA Champions Leagues => competitions
54
+ UEFA European Championship => competitions
55
+ UEFA Nations League => competitions
56
+ Champions League => competitions
57
+ European Championship => competitions
58
+ ```
59
+
60
+ ## Named Entity Recognition benchmark result
61
+
62
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317233cc92fd6fee317e030/Y5f7tK8lonGqeeO6L6bVI.png)
63
+
64
+ ## Model Authors
65
+ The model authors are:
66
+ * [Urchade Zaratiana](https://huggingface.co/urchade)
67
+ * Nadi Tomeh
68
+ * Pierre Holat
69
+ * Thierry Charnois
70
+
71
+ ## Citation
72
+ ```bibtex
73
+ @misc{zaratiana2023gliner,
74
+ title={GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer},
75
+ author={Urchade Zaratiana and Nadi Tomeh and Pierre Holat and Thierry Charnois},
76
+ year={2023},
77
+ eprint={2311.08526},
78
+ archivePrefix={arXiv},
79
+ primaryClass={cs.CL}
80
+ }
81
+ ```