|
|
--- |
|
|
model_name: Common Metaphors Detection Model |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- metaphor-detection |
|
|
- text-classification |
|
|
- transformers |
|
|
metrics: |
|
|
- accuracy: 64% |
|
|
- accuracy |
|
|
language: en |
|
|
dataset: Sasidhar1826/common_metaphors_detection_dataset |
|
|
datasets: |
|
|
- Sasidhar1826/common_metaphors_detection_dataset |
|
|
base_model: |
|
|
- google-bert/bert-base-uncased |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
|
|
|
# Common Metaphors Detection Model |
|
|
|
|
|
This model achieves an **accuracy of 64%** on **specific metaphor data of small dataset**. |
|
|
This is build upon **bert-base-uncased** |
|
|
this is not yet too much reliable to use in full scale as the metaphors meanings |
|
|
varies over the context of the sentences and the trained data is specific for only some cases. |
|
|
If you train it over **VU Amsterdam Metaphor Corpus** you can get better results in overall. |
|
|
|
|
|
## Usage |
|
|
You can load this model in your Hugging Face code as follows: |
|
|
```python |
|
|
from transformers import AutoModel |
|
|
|
|
|
model = AutoModel.from_pretrained('Sasidhar1826/common_metaphors_detection') |
