-
A brief introduction to the task and the dataset used
- I used this dataset from kaggle
- It has 4 categories World, Sports, Business ,Science/Technology
-
The preprocessing steps taken
- Used DistilBertTokenizer to tokenize the sentences
-
The architecture of the model used, and how it was fine-tuned
- I used distilbert-based-uncased model form huggingface and added two linear layers and one dropout layer for classification task
-
The evaluation metrics and the results obtained
- I used cross entrophy loss to calculate the loss
- After training 1 epoch with whole dataset and batch size of 16, the accuracy of model was 83.88% which is preety good for four classes and if i had trained for 5 epochs it could have reached 90% easily.
-
A discussion of the performance of the model and possible ways to improve it.
- I didnt had enough time to train the model so i was only able to get 83.88% accuracy, it could be improved by training for atleast 5 hours.
text-classification's Introduction
text-classification's People
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.