Instructor: Prof. Jung-Hsien Chiang (蔣榮先)
Course : Tue 2-4 ; Office Hour : Please make an appointment by email.
Course Goals
To understand and be able to apply information retrieval technology in automated biomedical literature search. Students will participate in intensive computer programming projects and will enhance their skills via research to various search technologies. This course also includes paper presentation and final project as well. Students will be expected to complete all course requirements upon their participation.
Course Outline
- Introduction
- Basic IR Modeling
- Retrieval Evaluation
- Document Processing
- Query Operation
- Word Embedding/BERT/LLM
- Indexing and Search
- Searching the Webs
- Social text Analytics/Image Retrieval
- LLM Challenge
Textbook
1.Manning, Raghavan, and Schutze, Introduction to Information Retrieval, Cambridge University Press, 2009
2.ChatGPT, Claude, or Gemini
References
Ricardo Baeza-Yates and Berthier Ribeiro-Neto, Modern Information Retrieval, Addison-Wesley Inc., 1999
Grading Policy
Computer Assignment 40%
Presentation 30%
Final Course Project 30%
Note :
* 每位修課同學隔週須獨力完成一個程式專案，並上台展示，一共6個專案
(Each student was asked to do 6 software tool-based projects for different subjects bi-weekly.)
專案主題如下: Followings are possible subjects for projects:
Keyword-based full text matching
Query expansion models
Indexing models
Multi-model (Text vs Image Retrieval)
Searching and Visualization the PubMed Documents
ChatGPT and LLM Family
** Each student requires to present 2 relevant papers by assignment.
Lecture Note
Supplementary
Homework