Semantic Data Course Projects

📁 Directory Tree:

.
├── README.md
├── 01-Paper_Presentations
│   ├── A New Algorithm for Data Compression
│   └── Improving Language Understanding by Generatove Pre-Training
├── 02-Markovify_Project
│   ├── Project_01   
│   └── Project_02 
├── 03-Movie_Reviews_Classification
│   ├── reviews_classification_01
│   ├── reviews_classification_02
│   └── reviews_classification_03
├── 04-LLM_Tricks
│   ├── LLM_tricks_01
│   └── LLM_tricks_02
└── 05-Final_Project

👥Percentage contribution for each group member:

Name	Paper presentations		Markovify projects	Movie reviews Classification	LLM tricks	Final project
	BPE	GPT-1
Gengcheng Lyu	25%	25%	25%	25%	25%	25%
Haoxue Zhuang	25%	25%	25%	25%	25%	25%
Mohammad Hossein Moradi	25%	25%	25%	25%	25%	25%
Nurul Khafifah Binti Ahmad Nassir	25%	25%	25%	25%	25%	25%

💡 Description for each part:

1. Paper_Presentations: We made two paper presentations, one is about a new algorithm for data compression and the other is about improving language understanding by generative pre-training. Both presentations are in the 01-Paper_Presentations directory.

2. Markovify_Project: We made two single projects for the Markovify library to generate sometext from corpus. All projects are in the 02-Markovify_Project directory.

3. Movie_Reviews_Classification: We made three single notebooks for classifying movie reviews into different categories. All notebooks are in the 03-Movie_Reviews_Classification directory.

4. LLM_Tricks: We made and found out two different tries for Large Language Model tricks which can bypass the security mechanism of language models. Both notes are in the 04-LLM_Tricks directory.

5. Final_Project: We made a final project about a chatbot that can let user chat with large documents. The project is in the 05-Final_Project directory.