Intent Recognition and classification with GRU, LSTM stacking, DeepPavlov and BERT models with the help of Tensorflow Keras and DeepPavlov framework.
Selected data is famously known intent classification dataset named SNIPS which is mostly used for model benchmarking in this specific topic.
Tensorboard viz of the loss and accuracy relationships of train and validation sets:
BERT achieves 90+ accuracy which is slightly more than the stacked GRU and LSTM model
Include: Numpy Pandas NLTK Re(gex) SkLearn Matplotlib Seaborn Tqdm Math Monkeylearn API Colab TFKeras BERT Deeppavlov
- Intent recognition
- Intent classification
- NLU
If you have questions or need further guidance on using this template, please file an issue. I will do my best to respond to all issues in a timely manner.
All contributions and suggestions are welcome!
For suggested improvements, please file an issue.
For direct contributions, please fork the repository and file a pull request. If you never created a pull request before, welcome ๐ ๐ Here is a great tutorial on how to send one.
In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to making participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, nationality, personal appearance, race, religion, or sexual identity and orientation.
This project is licensed under The Unlicense and released to the Public Domain. For more information see our LICENSE file.