|
|
|
|
|
|
Course Description
This is an especially exciting time to study Natural Language Processing (NLP), which aims to enable computers to understand and automatically process human language. This course will focus on NLP fundamentals including language models, automatic syntactic processing and automatic semantic processing, discourse and pragmatics. In addition, this course will also introduce various applications of NLP, including information extraction, sentiment analysis, question and answering, text summarization and machine translation. The students will digest and practice their NLP knowledge and skills by working on programming assignments, in-class quizzes and a final project.
Course Goal
Through this course, students will gain solid theoretical knowledge and enough practical experience to design and develop their own text processing applications in the future.Evaluation Metrics
You should expect for a lot of programming (four of them), frequent in-class quizzes (5 in total, roughly one after each two meetings), and a final project. In addition, you will be aawarded for active class participation, penalized for little participation. The good news is there's no final exam for this class!
| Four Programming Assignments: | 40% |
| Five in-class quizzes: | 20% |
| Class participation: | 10% |
| The Final Project: | 30% (abstract: 5%, presentation+report+code+data: 25%) |
The grading policy is as follows:
| 90-100: | A |
| 80-89: | B |
| 70-79: | C |
| 60-69: | D |
| <60: | F |
Attendance and Make-up Policies
Every student should attend the class, unless you have an accepted excuse. Please check student rule 7 http://student-rules.tamu.edu/rule07 for details.
Project
It's important that you work on a real nlp project so that you earn first hand experience of basic text processing and learn to deal with high complexity of human language in concrete applications. You are responsible to develop your project ideas. Then the instructor is available to discuss and shape the project if you like. The scale of the project should be a semester long. By the end of the semester, you should submit your code and data for this project, write a project report of 8 pages at maximum, and prepare a class presentation.
Prerequisite
Students should have taken the course Data Structure and Algorithms (CSCE 221).
Textbook and Material
Required textbook: Speech and Language Processing, Daniel Jurafsky and James H. Martin, 2008. Prentice Hall; 2nd edition. Relevant tutorials and papers will also be handed out during the class.
Academic Integrity
"An Aggie does not lie, cheat, or steal or tolerate those who do." For additional information, please visit: http://aggiehonor.tamu.edu.
Upon accepting admission to Texas A&M University, a student immediately assumes a commitment to uphold the Honor Code, to accept responsibility for learning, and to follow the philosophy and rules of the Honor System. Students will be required to state their commitment on examinations, research papers, and other academic work. Ignorance of the rules does not exclude any member of the TAMU community from the requirements or the processes of the Honor System.
Americans with Disabilities Act (ADA) Statement
The Americans with Disabilities Act (ADA) is a federal anti-discrimination statute that provides comprehensive civil rights protection for persons with disabilities. Among other things, this legislation requires that all students with disabilities be guaranteed a learning environment that provides for reasonable accommodation of their disabilities. If you believe you have a disability requiring an accommodation, please contact Disability Services, currently located in the Disability Services building at the Student Services at White Creek complex on west campus or call 979-845-1637. For additional information, visit http://disability.tamu.edu.
Tentative schedule
| Date | Topic | Material | Notes |
|---|---|---|---|
| Introduction | |||
| 01/17 | Course Overview | slides | |
| 01/19 | Text Preprocessing and Regular Expressions | slides | p1 out |
| Classification | |||
| 01/24 | Text Classification and Naive Bayes | slides | |
| 01/26 | Discriminative Models: MaxEnt,Perceptron | slides | |
| 01/31 | Discriminative Models: MaxEnt, Perceptron cont. | slides | p1 due, p2 out |
| Language Modeling | |||
| 02/02 | Language Modeling | slides | quiz1 Sentence-level LM Discourse Driven LM |
| 02/07 | Smoothing | slides | |
| Syntax | |||
| 02/09 | Intro to Parts-of-Speech Tagging | slides | |
| 02/14 | Sequence Models | slides | HMM, CRF p2 due |
| 02/16 | Sequence Models cont. | slides | p3 out |
| 02/21 | Intro to Parsing | slides | quiz2 |
| 02/23 | Statistical Parsing | slides | |
| 02/28 | Statistical Parsing cont. | slides | lexicalized PCFGs |
| 03/02 | Intro to Dependency Parsing | slides | project abstract due |
| Semantics | |||
| 03/07 | Intro to Semantics | slides | quiz3 -> 03/23 |
| 03/09 | Distributional Semantics | slides | p3 due |
| 03/14 | Spring Break | ||
| 03/16 | Spring Break | ||
| 03/21 | no class, out of town | ||
| 03/23 | Dense Vectors | slides | |
| 03/28 | Semantic Role Labeling | slides | |
| Information Extraction | |||
| 03/30 | intro to IE & sentiment lexicon induction | slides | p4 out |
| 04/04 | Relation Extraction | slides | quiz4 |
| 04/06 | Discourse, Pragmatics, Coreference Resolution | slides | |
| 04/11 | Discourse, Pragmatics, Coreference Resolution | slides | |
| 04/13 | Event Extraction | slides | p4 due |
| Deep Learning | |||
| 04/18 | Deep Learning | slides | quiz5, project due, deep learning for NLP |
| Projects | |||
| 04/20 | Final Project Presentations | slides | |
| 04/25 | Final Project Presentations | slides | |
| 04/27 | Final Project Presentations | slides | |