This repository is a part of track at FIRE 2019. We have used combinations of different word embedding techniques namely Glove, FastText, and Paragram. Our model is based on a Bidirectional LSTM-GRU network coupled with checkpoint ensembling for the fine-grained classification of insincere questions into the following categories:
- Rhetorical Questions
- Hate Speech
- Sexual Content
- Hypothetical Questions
- Other
- Sincere Question
The final code/model used can be found
The model architecture is shown below:
Our approach was awarded the First Prize for this competition with an overall F1 score of 67.32%
The link to the working notes for this paper can be found here: http://ceur-ws.org/Vol-2517/
The link to the paper is: http://ceur-ws.org/Vol-2517/T5-5.pdf
======================================================================================================
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
What things you need to install the software and how to install them
Give examples
A step by step series of examples that tell you how to get a development env running
Say what the step will be
Give the example
And repeat
until finished
End with an example of getting some data out of the system or using it for a little demo
Explain how to run the automated tests for this system
Explain what these tests test and why
Give an example
Explain what these tests test and why
Give an example
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.
We use SemVer for versioning. For the versions available, see the tags on this repository.
- Billie Thompson - Initial work - PurpleBooth
See also the list of contributors who participated in this project.
This project is licensed under the MIT License - see the LICENSE.md file for details
- Hat tip to anyone whose code was used
- Inspiration
- etc