Inspiration
Many documents with different subjects should be classified. Moreover, the task is boring for human.
What it does
It helps classify documents of US government. In other words, documents can be automatically classified based on their similar core content.
How we built it
We tried to find the similarity between tittles of each document and put them in their own cluster.
Challenges we ran into
Using KNN for text classifier is challenging and it requires time to master the technique.
Accomplishments that we're proud of
A stepping stone to gain more knowledge in NLP.
What we learned
Even though the project is not complete, we have been able to learn more about language processing
Built With
- notebook
- python
Log in or sign up for Devpost to join the conversation.