Spaces:
Running
Running
Commit
·
2222dbb
1
Parent(s):
593f17e
add markdown
Browse files
app.py
CHANGED
@@ -171,24 +171,22 @@ def _cached_predictions(state):
|
|
171 |
|
172 |
with gr.Blocks() as demo:
|
173 |
gr.Markdown("""# Data Use Detector
|
174 |
-
|
175 |
This Space demonstrates our fine-tuned GLiNER model’s ability to spot **dataset mentions** and **relations** in any input text. It identifies dataset names via NER, then extracts relations such as **publisher**, **acronym**, **publication year**, **data geography**, and more.
|
176 |
-
|
177 |
-
---
|
178 |
-
|
179 |
**How it works**
|
180 |
1. **NER**: Recognizes dataset names in your text.
|
181 |
2. **RE**: Links each dataset to its attributes (e.g., publisher, year, acronym).
|
182 |
3. **Visualization**: Highlights entities and relation spans inline.
|
183 |
-
|
184 |
**Instructions**
|
185 |
1. Paste or edit your text in the box below.
|
186 |
2. Tweak the **NER** & **RE** confidence sliders.
|
187 |
3. Click **Submit** to see highlights.
|
188 |
4. Click **Get Model Predictions** to view the raw JSON output.
|
189 |
-
|
190 |
**Resources**
|
191 |
-
- **Model:**
|
192 |
- **Paper:** _Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers_ – ArXiv: [2502.10263](https://arxiv.org/pdf/2502.10263)
|
193 |
- [GLiNER GitHub Repo](https://github.com/urchade/GLiNER)
|
194 |
- [Project Docs](https://worldbank.github.io/ai4data-use/docs/introduction.html)
|
|
|
171 |
|
172 |
with gr.Blocks() as demo:
|
173 |
gr.Markdown("""# Data Use Detector
|
174 |
+
|
175 |
This Space demonstrates our fine-tuned GLiNER model’s ability to spot **dataset mentions** and **relations** in any input text. It identifies dataset names via NER, then extracts relations such as **publisher**, **acronym**, **publication year**, **data geography**, and more.
|
176 |
+
|
|
|
|
|
177 |
**How it works**
|
178 |
1. **NER**: Recognizes dataset names in your text.
|
179 |
2. **RE**: Links each dataset to its attributes (e.g., publisher, year, acronym).
|
180 |
3. **Visualization**: Highlights entities and relation spans inline.
|
181 |
+
|
182 |
**Instructions**
|
183 |
1. Paste or edit your text in the box below.
|
184 |
2. Tweak the **NER** & **RE** confidence sliders.
|
185 |
3. Click **Submit** to see highlights.
|
186 |
4. Click **Get Model Predictions** to view the raw JSON output.
|
187 |
+
|
188 |
**Resources**
|
189 |
+
- **Model:** [rafmacalaba/gliner_re_finetuned-v3](https://huggingface.co/rafmacalaba/gliner_re_finetuned-v3)
|
190 |
- **Paper:** _Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers_ – ArXiv: [2502.10263](https://arxiv.org/pdf/2502.10263)
|
191 |
- [GLiNER GitHub Repo](https://github.com/urchade/GLiNER)
|
192 |
- [Project Docs](https://worldbank.github.io/ai4data-use/docs/introduction.html)
|