Token Classification
Transformers
PyTorch
English
roberta
keyphrase-extraction
Eval Results (legacy)
Instructions to use ml6team/keyphrase-extraction-kbir-kpcrowd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ml6team/keyphrase-extraction-kbir-kpcrowd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="ml6team/keyphrase-extraction-kbir-kpcrowd")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("ml6team/keyphrase-extraction-kbir-kpcrowd") model = AutoModelForTokenClassification.from_pretrained("ml6team/keyphrase-extraction-kbir-kpcrowd", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
23e4720
1
Parent(s): 0496356
Update README.md
Browse files
README.md
CHANGED
|
@@ -67,7 +67,6 @@ Sahrawat, Dhruva, Debanjan Mahata, Haimin Zhang, Mayank Kulkarni, Agniv Sharma,
|
|
| 67 |
* This keyphrase extraction model is very dataset-specific. It's not recommended to use this model for other domains, but you are free to test it out.
|
| 68 |
* Only works for English documents.
|
| 69 |
* Large number of annotated keyphrases.
|
| 70 |
-
* For a custom model, please consult the [training notebook]() for more information.
|
| 71 |
|
| 72 |
### ❓ How To Use
|
| 73 |
```python
|
|
@@ -147,8 +146,6 @@ print(keyphrases)
|
|
| 147 |
You can find more information in the [paper](https://arxiv.org/abs/1306.4606).
|
| 148 |
|
| 149 |
## 👷♂️ Training Procedure
|
| 150 |
-
For more in detail information, you can take a look at the [training notebook]().
|
| 151 |
-
|
| 152 |
### Training Parameters
|
| 153 |
|
| 154 |
| Parameter | Value |
|
|
@@ -264,7 +261,5 @@ The model achieves the following results on the Inspec test set:
|
|
| 264 |
|:-----------------:|:----:|:----:|:----:|:----:|:----:|:-----:|:----:|:----:|:----:|
|
| 265 |
| Inspec Test Set | 0.47 | 0.07 | 0.12 | 0.46 | 0.13 | 0.20 | 0.37 | 0.33 | 0.33 |
|
| 266 |
|
| 267 |
-
For more information on the evaluation process, you can take a look at the keyphrase extraction [evaluation notebook]().
|
| 268 |
-
|
| 269 |
## 🚨 Issues
|
| 270 |
Please feel free to start discussions in the Community Tab.
|
|
|
|
| 67 |
* This keyphrase extraction model is very dataset-specific. It's not recommended to use this model for other domains, but you are free to test it out.
|
| 68 |
* Only works for English documents.
|
| 69 |
* Large number of annotated keyphrases.
|
|
|
|
| 70 |
|
| 71 |
### ❓ How To Use
|
| 72 |
```python
|
|
|
|
| 146 |
You can find more information in the [paper](https://arxiv.org/abs/1306.4606).
|
| 147 |
|
| 148 |
## 👷♂️ Training Procedure
|
|
|
|
|
|
|
| 149 |
### Training Parameters
|
| 150 |
|
| 151 |
| Parameter | Value |
|
|
|
|
| 261 |
|:-----------------:|:----:|:----:|:----:|:----:|:----:|:-----:|:----:|:----:|:----:|
|
| 262 |
| Inspec Test Set | 0.47 | 0.07 | 0.12 | 0.46 | 0.13 | 0.20 | 0.37 | 0.33 | 0.33 |
|
| 263 |
|
|
|
|
|
|
|
| 264 |
## 🚨 Issues
|
| 265 |
Please feel free to start discussions in the Community Tab.
|