urchade commited on
Commit
108bed9
1 Parent(s): 306251f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -10
README.md CHANGED
@@ -8,17 +8,77 @@ pipeline_tag: token-classification
8
  library_name: gliner
9
  ---
10
 
11
- GLiNER-M trained with *"urchade/pile-mistral-v0.1"* which is commercially permissible.
12
 
13
- This version is slightly better (at least comparable) than *"urchade/gliner_medium"* and *"urchade/gliner_base"*. Use with ```threshold=0.3``` for better performance.
14
 
 
 
 
 
 
 
 
 
 
15
  ```
16
- CrossNER_AI : 52.0%
17
- CrossNER_literature : 62.6%
18
- CrossNER_music : 68.9%
19
- CrossNER_politics : 65.7%
20
- CrossNER_science : 65.2%
21
- mit-movie : 46.5%
22
- mit-restaurant : 30.9%
23
- Average : 56.0%
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  ```
 
8
  library_name: gliner
9
  ---
10
 
11
+ # About
12
 
13
+ 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.
14
 
15
+ This version has been trained on the **NuNER** dataset (commercially permissive)
16
+
17
+ ## Links
18
+
19
+ * Paper: https://arxiv.org/abs/2311.08526
20
+ * Repository: https://github.com/urchade/GLiNER
21
+
22
+ ## Installation
23
+ To use this model, you must install the GLiNER Python library:
24
  ```
25
+ !pip install gliner
26
+ ```
27
+
28
+ ## Usage
29
+ 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`.
30
+
31
+ ```python
32
+ from gliner import GLiNER
33
+
34
+ model = GLiNER.from_pretrained("urchade/gliner_mediumv2.1")
35
+
36
+ text = """
37
+ 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.
38
+ """
39
+
40
+ labels = ["person", "award", "date", "competitions", "teams"]
41
+
42
+ entities = model.predict_entities(text, labels)
43
+
44
+ for entity in entities:
45
+ print(entity["text"], "=>", entity["label"])
46
+ ```
47
+
48
+ ```
49
+ Cristiano Ronaldo dos Santos Aveiro => person
50
+ 5 February 1985 => date
51
+ Al Nassr => teams
52
+ Portugal national team => teams
53
+ Ballon d'Or => award
54
+ UEFA Men's Player of the Year Awards => award
55
+ European Golden Shoes => award
56
+ UEFA Champions Leagues => competitions
57
+ UEFA European Championship => competitions
58
+ UEFA Nations League => competitions
59
+ Champions League => competitions
60
+ European Championship => competitions
61
+ ```
62
+
63
+ ## Named Entity Recognition benchmark result
64
+
65
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317233cc92fd6fee317e030/Y5f7tK8lonGqeeO6L6bVI.png)
66
+
67
+ ## Model Authors
68
+ The model authors are:
69
+ * [Urchade Zaratiana](https://huggingface.co/urchade)
70
+ * Nadi Tomeh
71
+ * Pierre Holat
72
+ * Thierry Charnois
73
+
74
+ ## Citation
75
+ ```bibtex
76
+ @misc{zaratiana2023gliner,
77
+ title={GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer},
78
+ author={Urchade Zaratiana and Nadi Tomeh and Pierre Holat and Thierry Charnois},
79
+ year={2023},
80
+ eprint={2311.08526},
81
+ archivePrefix={arXiv},
82
+ primaryClass={cs.CL}
83
+ }
84
  ```