Downloads · 30 days
9
1% of all-time downloads
blaze-it-ner
osiria/blaze-it-ner
blaze-it-ner is a token classification model from osiria. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
--------------------------------------------------------------------------------------------------
All-time downloads
745
Public
Parameters
53.5M
428 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin214 MB · 50%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- May 2, 2023
- Updated
- Dec 16, 2024
- SHA
- 3d4fcc68
Try a prompt
Spaces
Model card
From the Hugging Face model README
<body> <span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span> <br> <span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> Task: Named Entity Recognition</span> <br> <span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: BLAZE 🔥</span> <br> <span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span> <br> <span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> Type: Uncased</span> <br> <span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span> </body>
<h3>Model description</h3>
This is a lightweight and uncased model for the <b>Italian</b> language, fine-tuned for <b>Named Entity Recognition</b> (<b>Person</b>, <b>Location</b>, <b>Organization</b> and <b>Miscellanea</b> classes) on the WikiNER dataset <b>[1]</b>, using <b>Blaze-IT</b> (blaze-it) as a pre-trained model.
<h3>Training and Performances</h3>The model is trained to perform entity recognition over 4 classes: <b>PER</b> (persons), <b>LOC</b> (locations), <b>ORG</b> (organizations), <b>MISC</b> (miscellanea, mainly events, products and services). It has been fine-tuned for Named Entity Recognition, using the WikiNER Italian dataset plus an additional custom dataset of manually annotated Wikipedia paragraphs. The model has been trained for 1 epoch with a constant learning rate of 1e-5.
The 5-fold cross-validated performances on the test set are reported in the following table:
| Recall | Precision | F1 |
|---|---|---|
| 89.29 | 89.84 | 89.53 |
The metrics have been computed at the token level and then macro-averaged over the 4 classes.
Then, since WikiNER is an automatically annotated (silver standard) dataset, which sometimes contains imperfect annotations, an additional fine-tuning on ~3.500 manually annotated paragraphs has been performed.
You can try the model online using this web app: https://huggingface.co/spaces/osiria/blaze-it-demo
<h3>References</h3>[1] https://www.sciencedirect.com/science/article/pii/S0004370212000276
<h3>Limitations</h3>This model is mainly trained on Wikipedia, so it's particularly suitable for natively digital text from the world wide web, written in a correct and fluent form (like wikis, web pages, news, etc.). However, it may show limitations when it comes to chaotic text, containing errors and slang expressions (like social media posts) or when it comes to domain-specific text (like medical, financial or legal content).
<h3>License</h3>The model is released under <b>Apache-2.0</b> license
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Languages
- it
- Created
- May 2, 2023
- Updated
- Dec 16, 2024