Course Assignments
Welcome to the assignments for PSYC 51.17: Models of Language and Communication.
Submission Instructions
All assignments are submitted via GitHub Classroom. Click the "Accept Assignment" button on each assignment page to get started. This will create a personal repository where you'll complete your work.
Submission Process:
- Click "Accept Assignment" to create your repository
- Clone the repository to your local machine or open in Google Colab
- Complete the assignment following the instructions
- Commit and push your changes before the deadline
- Your latest commit before the deadline will be graded
Assignment Schedule
| # | Title | Released | Due | Weight |
|---|---|---|---|---|
| 1 | ELIZA Chatbot | Week 1 (Jan 9) | Jan 16, 11:59 PM EST | 15% |
| 2 | SPAM Classifier | Week 2 (Jan 16) | Jan 23, 11:59 PM EST | 15% |
| 3 | Wikipedia Embeddings | Week 3 (Jan 23) | Jan 30, 11:59 PM EST | 15% |
| 4 | Customer Service Chatbot | Week 4 (Jan 30) | Feb 6, 11:59 PM EST | 15% |
| 5 | Build GPT | Week 6 (Feb 9) | Feb 13, 11:59 PM EST | 15% |
| Final | Research Project | Week 9 (Mar 4) | Mar 9, 11:59 PM EST | 25% |
Late Policy
Assignments receive a 10% deduction for each week late, rounded up to the nearest whole week. The final project must be submitted on time.
Grading
Each assignment is graded on:
- Correctness: Does your code produce the expected outputs?
- Code Quality: Is your code well-organized and documented?
- Understanding: Do your explanations demonstrate understanding of the concepts?
Getting Help
- Office Hours: By appointment
- Discord: Join our class server for discussions
- GitHub Issues: Report bugs or ask questions on the assignment repositories
Assignments
Assignment 1: ELIZA Chatbot
Build a pattern-matching chatbot based on Weizenbaum's classic ELIZA program. Learn about string manipulation, regular expressions, and the foundations of conversational AI.
Assignment 2: SPAM Classifier
Develop a text classification system to identify spam messages. Explore feature engineering, tokenization, and evaluation metrics.
Assignment 3: Wikipedia Embeddings
Compare different text embedding methods on Wikipedia articles. Visualize semantic relationships and evaluate embedding quality.
Assignment 4: Customer Service Chatbot
Create a context-aware customer service chatbot using transformer-based models. Implement retrieval and response generation.
Assignment 5: Build GPT
Implement and train a small GPT model from scratch. Understand the transformer architecture, attention mechanisms, and autoregressive generation.
Final Project: Research Project
Conduct an independent research project applying concepts from the course. Present your findings to the class.