Sovereign 8s.is mirror of standardgalactic/COSMO-MT
- Python 100%
| Filename | Latest commit message | Latest commit date |
|---|---|---|
| Data_Preprocessing.py | ||
| Feature_Vector.py | ||
| Main.py | ||
| README.md | ||
Proposed COSMO-MT model
The proposed COSMO-MT model is a new deep learning-based multi-task model to perform Sentiment Classifiction (SC) and Emotion Detection (ED) tasks. It consists of input, embedding, shared and task-specific, dense, and output layers. Each layer is responsible to perform a specific function that supports both SC and ED. In addtion to that four groups of hand-crafted shallow which consist of 15 auxiliary features making the model well-informed. The proposed model is evaluated over two benchmark datasets and it performs significantly better than the comparable methods.
Pre-requisite:
- Keras 2.2.4
- Numpy
- Pandas
- Python 3.7
- BERT
- Tensorflow 1.15
- NLTK