國立中興大學教學大綱

課程名稱	(中) 資訊檢索(6658)
	(Eng.) Advanced Topics in Information Retrieval
開課單位	資工系
課程類別	選修	學分	3	授課教師	范耀中
選課單位	資工系 / 碩士班	授課使用語言	中文	英文/EMI		開課學期	1141
課程簡述	As the amount of text data, such as web pages and blogs, grows explosively, it is increasingly important to develop tools to help us manage the huge amount of information. Web search engines are good examples of such tools. In this course, you will learn the underlying technologies behind the Web search engines and Information Retrieval. This course will cover traditional material as well as recent advances in Information Retrieval. You will be able to learn the basic principles and algorithms for managing, indexing, query, and classifying text data. Also, we will introduce deep learning techniques on text processing, including word2vec, fasttext, glove, transformer, BERT models.
先修課程名稱						課程含自主學習	Y

課程與核心能力關聯配比(%)

課程目標之教學方法與評量方法

課程目標

核心能力

配比(%)

教學方法

評量方法

To learn the related knowledge of information retrieval.
To learn the related knowledge of natural language processing

專題探討/製作

討論

講授

口頭報告

作業

測驗

授課內容(單元名稱與內容、習作/每週授課、考試進度-共16週加自主學習)

週次	授課內容
第1週	- Introduction: Goals and history of IR. The impact of the web on IR.
第2週	- Basic IR Models: Boolean and vector-space retrieval models; ranked retrieval; text-similarity metrics; TF-IDF (term frequency/inverse document frequency) weighting; cosine similarity.
第3週	- Basic Tokenizing, Indexing, and Implementation of Vector-Space Retrieval: Simple tokenizing, stop-word removal, and stemming; inverted indices; efficient processing with sparse vectors; Java implementation.
第4週	- Experimental Evaluation of IR: Performance metrics: recall, precision, and F-measure; Evaluations on benchmark text collections.
第5週	- Page Rank - Web Search: Link Analysis, HITS algorithm
第6週	- Midterm Exam
第7週	- Word2vec, Word Embedding
第8週	- RNN, Transformer, Attention Mechanism
第9週	- BERT and Pretrained Language Model
第10週	- Reading Comprehension Model - Language Generation Model
第11週	- Project Proposal
第12週	- Paper Presentation
第13週	- Paper Presentation
第14週	- Paper Presentation
第15週	自主學習：EM (Expectation-Maximization) algorithm
第16週	自主學習：Rocchio algorithm for Relevance Feedback - Project Demo - Final Exam
自主學習內容

學習評量方式

1. Programming Assignment 20%
2. Midterm 20%
3. Final Exam: 20%
4. Project 20 %
5. Paper Presentation 20%

教科書＆參考書目(書名、作者、書局、代理商、說明)

1. Manning, Introduction to Information Retrieval.
2. Dive into Deep Learning

課程教材（教師個人網址請列在本校內之網址）

N/A

課程輔導時間

By appointment

聯合國全球永續發展目標(連結網址)

提供體驗課程：N

請尊重智慧財產權及性別平等意識，不得非法影印他人著作。
更新日期西元年/月/日：無	列印日期西元年/月/日：2025 / 8 / 03
MyTB教科書訂購平台：http://www.mytb.com.tw/