Date |
Subject |
In-class Activies & Hours |
After Class Activies & Hours |
9/16 |
Introduction to NLP
An overview of natural language processing
|
Lecture: 3 hours |
Post-lecture review: 3 hours |
9/23 |
Linguistic Essentials
A breif introduction of linguistics and its applications in NLP
|
Lecture: 3 hours |
Post-lecture review: 3 hours |
9/30 |
Collocation
Mining collocated words from a collection of documents
|
Lecture: 3 hours |
Post-lecture review: 3 hours
|
10/7 |
Language Modeling
The basic concepts of language modeling and its applications. The smoothing algorithms are also described. In addition, word embeddings, which are distributed word representation obtained by the recurrent neural network, are very useful in many applications. Basic models for training word embeddings including CBOW, Skipgram, and Fasttext, will be given.
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Assignment: 6 hours
|
10/14 |
Wod Sense Disambiguation
Two approaches to word sense disambiguation.
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Assignment: 6 hours
|
10/21 |
Final Project Announcement
Giving the overview and the description of the final project.
|
Lecture: 3 hours |
Post-lecture review: 3 hours |
10/28 |
Text Classification
Basic statistical models for text classification and feature extraction.
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Assignment: 6 hours
|
11/4 |
POS Tagging
Introduction to sequence labeling and its important application in NLP including part-of-speech tagging. POS tagging in both Chinese and English will be described.
|
Lecture: 3 hours |
Pre-exam review: 12 hours |
11/11 |
Midterm Exam |
Exam: 3 hours |
|
11/18 |
Chinese Word Segmentation
Chinese word segmentation is a special subject in NLP. How to perform text segmentation with sequence labeling will be introduced.
Final project announcement
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Assignment: 6 hours
Final project: 6 to N hours
|
11/25 |
Neural Networks for NLP
Deep nueral networks play an important role in modern NLP. This subject introduces the convolutional neural network (CNN) and recurrent neural network (RNN) in NLP.
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Assignment: 6 hours
Final project: 6 to N hours
|
12/2 |
Advanced Neural Networks for NLP
The most recent methodology, pre-trained Transformer-based text encoding, which is very powerful and widely-used in almost all NLP tasks, will be covered. How to do NLP with BERT and T5 will be demonstrated.
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Assignment: 6 hours
Final project: 6 to N hours
|
12/9 |
Parsing
Parse tree provides rich information in natural language understanding. This subject introduces two basic parsing schemes and computational models for parsing.
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Assignment: 6 hours
Final project: 6 to N hours
|
12/16 |
Discourse Analysis
Many novel applications are based on discourse analysis. This subject introduces discourse relation recognition and discourse parsing. Other topics in discourse analysis will be briefly described.
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Final project: 6 to N hours
|
12/23 |
Semi-supervised Approaches to NLP
Semi-supervised learning is extremely useful in NLP because training data is usually insufficient in novel tasks. The strategies for training models in the semi-supervised fashion will be introduced.
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Assignment: 6 hours
Final project: 6 to N hours
|
12/30 |
Invited Talk: NLP and Cyber Security (Temp.)
|
Lecture: 3 hours |
Post-lecture review: 3 hours
Final project: 6 to N hours
|
1/6 |
Final Project
Presentation of the final project
|
Presentation: 3 hours |
Pre-exam review: 12 hours |
1/13 |
Term Exam |
Exam: 3 hours |
|