Solving problems related to Natural Language Processing. 🗃️
Challenge | Integrations | Technologies | Getting Started | License
The project was developed as a challenge to create a API Rest that solves the following problems related to Natural Language Processing:
- The complete vocabulary formed by the isolated words.
- The complete vocabulary formed by groups of 2 words in sequence (2-gram).
- The numbers (n) of word vectors in all documents, considering the vocabulary formed by isolated words.
- The number (n) word vectors of all documents, considering the vocabulary formed by groups of 2 words in sequence (2-gram).
This project is part of the Clustering Words system, the other projects are located at:
The main technologies used to develop the project were:
This project was bootstrapped with:
First, make sure you have Node and Mongodb, then clone the project with:
git clone https://github.com/danieljpgo/clustering-words-backend.git
With npm, install dependencies:
npm install
In order to start the datebase, run:
sudo service mongod start
In order to start the application in a development environment, execute:
npm run dev
Any questions or problems access the links to the main technologies mentioned in Technologies.
This project is under the MIT license.
Developed by Daniel Jorge