|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- text-classification |
|
|
- quantization |
|
|
- fine-tuning |
|
|
base_model: |
|
|
- allenai/scibert_scivocab_uncased |
|
|
--- |
|
|
|
|
|
# Model Card for Research Paper Annotation Classifier |
|
|
|
|
|
This model is a fine-tuned version of a pre-trained model for text classification. It is specifically designed to classify sentences from research papers into annotation categories. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Annotation Categories |
|
|
|
|
|
- **Methodology (0):** Describes methods or techniques used. |
|
|
- **None (1):** Content irrelevant for annotation. |
|
|
- **Novelty (2):** Highlights novel contributions. |
|
|
- **Past Work (3):** References or compares past research. |
|
|
- **Result (4):** Discusses experimental results or findings. |
|
|
|
|
|
### Model Description |
|
|
|
|
|
This model is part of the 🤗 Transformers library and has been fine-tuned to enable efficient annotation of academic texts. It takes a single sentence as input and predicts one of the five predefined categories to streamline the research annotation process. |
|
|
|
|
|
- **Developed by:** Ashutosh Adhikari |
|
|
- **Model type:** Fine-tuned text classification model |
|
|
- **Language(s) (NLP):** English |
|
|
- **License:** Apache 2.0 |
|
|
- **Finetuned from model:** `allenai/scibert_scivocab_uncased` |
|
|
|
|
|
### Model Sources |
|
|
|
|
|
- **Repository:** N/A |
|
|
- **Paper:** N/A |
|
|
- **Demo:** N/A |
|
|
|
|
|
## Uses |
|
|
|
|
|
### Direct Use |
|
|
|
|
|
This model can be used as a standalone text classifier to annotate sentences from research papers based on their semantic content. |
|
|
|
|
|
### Downstream Use |
|
|
|
|
|
The model can be fine-tuned further for similar tasks, such as classifying academic content in specific domains. |
|
|
|
|
|
### Out-of-Scope Use |
|
|
|
|
|
The model is not suitable for multi-paragraph classification or non-academic text. |
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
|
|
The model has been trained on specific datasets derived from research papers, so it may not generalize well to other domains or languages. |
|
|
|
|
|
### Recommendations |
|
|
|
|
|
Users should evaluate the model’s performance on their specific data and consider fine-tuning for domain-specific tasks. |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
```python |
|
|
from transformers import pipeline |
|
|
|
|
|
classifier = pipeline("text-classification", model="AshutoshAdhikari/rsclf-scibert-improved") |
|
|
result = classifier("This paper introduces a novel technique for...") |
|
|
print(result) |
