Commit
·
3db5217
1
Parent(s):
64ca3b7
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,7 @@ NuNerZero - is the family of Zero-Shot Entity Recognition models inspired by [GL
|
|
| 19 |
The key differences between NuNerZero Token Long in comparison to GLiNER are:
|
| 20 |
* **4096 context window!** vs 512-token context in GLiNER. This allows processing a page at a time vs a few sentences!
|
| 21 |
* The possibility to **detect entities that are longer than 12 tokens**, as NuNerZero, it operates on the token level rather than on the span level.
|
|
|
|
| 22 |
* NuZero family is trained on the **diverse dataset tailored for real-life use cases** - NuNER v2.0 dataset
|
| 23 |
|
| 24 |
<p align="center">
|
|
|
|
| 19 |
The key differences between NuNerZero Token Long in comparison to GLiNER are:
|
| 20 |
* **4096 context window!** vs 512-token context in GLiNER. This allows processing a page at a time vs a few sentences!
|
| 21 |
* The possibility to **detect entities that are longer than 12 tokens**, as NuNerZero, it operates on the token level rather than on the span level.
|
| 22 |
+
* a more powerful version of GLiNER-large-v2.1, surpassing it by +1% on average
|
| 23 |
* NuZero family is trained on the **diverse dataset tailored for real-life use cases** - NuNER v2.0 dataset
|
| 24 |
|
| 25 |
<p align="center">
|