| # Dependency-parser | |
| ## Dependencies : | |
| * OS : Ubuntu 22.04.3 LTS | |
| * Python 3.7 | |
| * flask 1.1.1 | |
| * flask-wtf 0.14.2 | |
| * flask-markdown 0.3 | |
| * nltk 3.4.5 | |
| * pygraphviz 1.7 | |
| * conllu 2.2.2 | |
| * scikit-learn 0.22.1 | |
| * dill 0.3.1.1 | |
| * transformers 2.1.1 | |
| ```bash | |
| > python3.7 -m pip install torch==1.7.1+cu110 torchvision==0.8.2+cu110 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html | |
| ``` | |
| ## Instructions for web app : | |
| Run the following to host the app at localhost:5000 | |
| ```bash | |
| > python3.7 app.py | |
| ``` | |
| ## Results : | |
| Trained a model using <b>BERT</b> and parser implemented from <b>Deep Biaffine Attention for Neural Dependency Parsing</b> on Telugu UD Treebank dataset | |
| <b> | |
| train: 400 sentences | |
| </b> | |
| <br> | |
| <b> | |
| dev: 80 sentences | |
| </b> | |
| <br> | |
| <b> | |
| test: 120 sentences | |
| </b> | |
| ### Train | |
| Training the model | |
|  | |
| ### Evaluate | |
| Evaluation score after testing with Test Dataset | |
|  | |
| ### Prediction | |
| #### Entering the sentence | |
|  | |
| #### Final Result | |
|  | |
| #### Original Values | |
|  | |