This is the second deployment project which is part of the MLE Nanodegree. Detecting plagiarism is an active area of research; the task is non-trivial and the differences between paraphrased answers and original work are often not so obvious. In this project, a plagiarism detector is developed that examines a text file and performs binary classification; labeling that file as either plagiarized or not, depending on how similar that text file is to a provided source text.
This project is broken down into three main notebooks:
- Load in the corpus of plagiarism text data.
- Explore the existing data features and the data distribution.
- Clean and pre-process the text data.
- Define features for comparing the similarity of an answer text and a source text, and extract similarity features.
- Select "good" features, by analyzing the correlations between different features.
- Create train/test .csv files that hold the relevant features and class labels for train/test data points.
- Upload train/test feature data to S3.
- Define a binary classification model and a training script.
- Train the model and deploy it using SageMaker.
- Evaluate deployed classifier.
- AWS Account
- Experience with model development on AWS SageMaker
- Familiarity AWS S3
cd SageMaker
git clone https://github.com/rohanjn98/plagiarism-detection-sagemaker.git
exit