Web Intelligence & Message Understanding

課程內容

1. Web Basics: World Wide Web & User Generated Content (UGC)

   • Web Crawler & Scraping (API, NoAPI, Selenium)

   • Information Retrieval & Search Engine

2. Machine Learning & DNN Review

   • Supervised learning

   • Neural Networks: CNN, RNN, Attention

3. Text Processing & Representation 

   • Text wrangling and pre-processing

   • Word Embedding

   • Representation Learning 

4. Text Classification 

   • Event Detection

   • Sentiment Analysis

5. Web Data Extraction

   • BoilerPlate Removal / Main Content Extraction (吳昱豪)

   • Search Result Extraction (吳承儒)

   • Table Extraction

6. Natural Language Processing 

   • Parts of speech (POS) Tagging

   • Shallow Parsing

   • Constituency and Dependency Parsing

7. Information Extraction from UGC

   • Sequence Labeling (CRF, BiLSTM-CRF)

   • Named Entity Recognition 

8. Multi-Task Learning & Joint Learning: 

   • Aspect Based Sentiment Analysis (岱融+筱雯)

9. Extraction-based Question Answering 

   • Coreference Resolution  

10. Reinforcement Learning: Event Source Discovery (于晴)  

11. 期末專題: 

    • Text Summarization

    • Natural Language 2 Bash

資源

• Dive into Deep Learning by 

• Text analytics with python - 2nd edition

• Deep Learning for Human Language Processing by Prof. Hung-Yi Lee@NTU

• A Practitioner's Guide to Natural Language Processing (Part I) — Processing & Understanding Text