# CSE8803 DLT: Deep Learning for Text Data (2024 Fall)

## Table of Contents

## Logistics

**Instructor**: Chao Zhang**Teaching Assistant**: Yinghao Li (yinghaoli@gatech.edu); Haorui Wang (hwang984@gatech.edu)**Piazza**: https://piazza.com/gatech/fall2024/cse8803dlt**Office Hours**:- Instructor Office Hour: Tue 12:15-1PM, Open area outside Klaus 1447
- TA Office Hour: Thu 12:15-1PM, Klaus 3121

## Learning Objective

This course will introduce state-of-the-art machine learning techniques for
mainstay problems in text data analysis, with particular emphasis on **deep
learning methods** and **large language models** that have recently achieved enormous success. Students will
learn about trending problems in this field, key methods for solving these
problems, and their advantages and disadvantages. The students are also expected
to read, present, and discuss research papers, as well as conduct a research
oriented course project.

The learning objective is that by the end of this course, the students are able to formulate their text analysis problems at hand, choose appropriate models for the problems, and even come up with innovative solutions for solving open research problems in this field. The course will be useful for students who want to solve practical problems involving text data, and also for those who want to do edge-cutting research in text mining, natural language processing, artificial intelligence, and NLP-driven interdisciplinary research.

Prerequisites for this course: the students should be familiar with machine learning and have taken a relevant course before (e.g., CX4240, CSE6740, CS4641); (2) the students should be comfortable with reading research papers and giving presentations; (3) the students should have solid programming skills—the course project can be programming demanding.

## Schedule

Date | Topic | Presentation | Due |
---|---|---|---|

08/20/2024 | Course Overview | Piazza Signup; Paper Pickup | |

08/22/2024 | Machine Learning Review | ||

08/27/2024 | Embedding & Representation Learning | Paper Presentation Signup Open Aug 27 | |

08/29/2024 | Project Guideline and Examples | Paper Presentation Signup Close | |

09/03/2024 | Module 1: Transformers |
||

09/05/2024 | Attention & Transformer | P1 and P2 | HW1 Out |

09/10/2024 | Mixture-Of-Experts | P3 and P4 | |

09/12/2024 | Fast Attention | P5 and P6 | |

09/17/2024 | Module 2: Language Model Pre-Training |
HW1 Due | |

09/19/2024 | Encoder-Only & Encoder-Decoder (BERT, T5) | P7 and P8 | |

09/24/2024 | Decoder-Only (GPT3, Deepseek) | P9 and P10 | |

09/26/2024 | Scalable Training | P11 and P12 | HW2 Out |

10/01/2024 | Scalable Inference | P13 and P14 | |

10/03/2024 | Module 3: LLM Instruction Fine-Tuning |
||

10/08/2024 | Prompting Techniques | P15 and P16 | |

10/10/2024 | Project Checkpoint |
HW2 Due | |

10/15/2024 | No Class (Fall Break) | ||

10/17/2024 | Instruction Fine-Tuning | P17 and P18 | |

10/22/2024 | Efficient Fine-Tuning | P19 and P20 | HW3 Out |

10/24/2024 | Module 4: LLM Alignment |
||

10/29/2024 | Reward Modeling | P21 and P22 | |

10/31/2024 | RLHF Algorithms | P23 and P24 | |

11/05/2024 | RL from AI Feedback | P25 and P26 | HW3 Due, Project Pre-Signup Open |

11/07/2024 | Module 5: Multimodal LLM & LLM Agent |
Project Signup Open | |

11/12/2024 | Multimodal LLMs | P27 and P28 | |

11/14/2024 | LLM Agents | P29 and P30 | |

11/19/2024 | Project Presentations | ||

11/21/2024 | Project Presentations | ||

11/26/2024 | Project Presentations | ||

11/28/2024 | No Class | ||

12/03/2024 | No Class | ||

12/08/2023 | Project Report Due |

*Disclaimer: The instructor reserves the right to modify the planned schedule and grading policy as needed during the course.*

## Grading

### Homework (30%)

- There will be three assignments. Each one will test your understanding of the taught methods or the presented papers.
- Late policy: Assignments are due at 11:59PM of the due date. You will be allowed 2 total late days without penalty for the entire semester. Once those days are used, you will be penalized according to the following policy:
- Homework is worth full credit before the due time.
- It is worth 75% credit for the next 24 hours.
- It is worth 50% credit for the second next 24 hours.
- It is worth zero credit after that.

- Follow the Georgia Tech Academic Honor Code.

### Paper Presentation (25%)

- We have 30 papers to study, and you will need to pick one paper from the list to present. The paper list and presentation sign-up sheet is available here (will be open for signup on Aug 27 at 3PM ET).
- Each presentation is 20 minutes, plus 10 minutes for Q&A and discussion. Each presentation can be done by up to three presenters.
- You need to post your slides by 9pm EST the night before your presentation.
- The presentation will be graded by the instructor according to the following criteria: quality of slides, presentation clearness, and question addressing. Your presentation should cover at least the following aspects: 1) What is the problem and background? 2) What are the main challenges of the problem? 3) How does the proposed method work? 4) What are the experimental results and observations?
- If you miss the presentation, unfortunately you will receive zero credit.
- Useful tips for presentation:
- Presentation Tips by Jeff Radel
- Oral Presentation Advice by Mark D. Hill

### Project (45%)

You need to complete a project on deep learning for text data. Your project needs to be clear about 1) the problem you are attempting to solve; 2) a survey of existing literature for the problem; 3) the technical method you propose in order to solve the problem; 4) the results and conclusion you attain.

- Each project needs to be completed in a team of 2-5 people. Team members need to clearly claim their contributions in the project report.
- You will need to do the following:
- Presentation (20%): group-wise project presentation
- Final report (25%): a complete and final project report

- The presentation schedule is available here (will be open for signup Nov 16 at 3pm)
- Here are some project guidelines and resources you may find useful.

## More Resources

- Speech and Language Processing, by Dan Jurafsky and James H. Martin
- Deep Learning for NLP
- Deep Learning, by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
- Dive into Deep Learning, by Aston Zhang, Zack C. Lipton, Mu Li, and Alex Smola

Other resources, such as deep learning toolboxes and datasets, will be provided throughout the course.