| Course introduction | |
|---|---|
| Course name | Statistical Natural Language Processing |
| Credits | 3 |
| Instructor | Bahram Vazirnezhad- Ph.D. in Biomedical Engineering- Bio-Electric |
| Schedules | Saturdays and Tuesdays 8:00-9:30, DLL 1st floor AVR and SLP Lab |
| Office hours | See office hours |
| General purpose | This course will focus on basic to advanced statistical techniques and methods in natural language and speech processing and its applications on speech and language technologies such as machine translation, question answering, language modeling, document clustering, speech processing. The syllabus contains mathematical foundations including probability theory, information theory, hypothesis testing, statistical inference, hidden markov models and statistical speech and language processing and its applications in part-of-speech tagging, machine translation, document clustering, document classification, speech enhancement, speech recognition and speech synthesis etc. |
| Course outline | Seminars
Homeworks Projects Exams |
| Required material | Electronic version of material are available HERE and hardcopies will be made available as required |
| Main reference | Probability, Random Variables and Stochastic Processes, A. Papoulis
An introduction to Computational Linguistics, R. Grishman Foundations of Statistical Natural Language Processing, C. Manning, H. Schutze Advanced Digital Signal Processing and Noise Reduction, S. Vaseghi Spoken Language Processing, X. Huang, A. Acero, H. Hon Discrete Time Processing of Speech Signals, J. R. Deller, J. H. L. Hansen, J. G. Proakis Statistical Machine Translation, P. Koehn |
| Evaluation | Class activity/ effective presence/ homeworks 25%
Seminars 20% Projects 35% Final exam 20% |
| Notes | -
- |
| Course syllabus | ||||
|---|---|---|---|---|
| Week | Description | Lecture | Homework | Notes |
| 1 | Introduction and course outline | lectures | homeworks | The purpose, content and organization of the course, required material; evaluation; preparing schedule for presentations etc. |
| 2 | Fundamentals- Probability, Statistics and Random Variables | lecture 1 | homework 1 | |
| 3 | Fundamentals- Statistics, Stochastic Processes and Fourier Transform | lecture 3 | homework 3 | |
| 4 | Fundamentals- Syntax, Chomsky hierarchy of languages | lecture 4 | homework 4 | |
| 5 | Fundamentals- Information theory and Entropy | lecture 5 | homework 5 | |
| 6 | Methods and Algorithms- Statistical pattern recognition, Baysian inference, Clustering algorithms (K-means, KNN) | lecture 6 | homework 6 | |
| 7 | Methods and Algorithms- Statistical pattern recognition, Decision trees, PCA, Least Square | lecture 7 | homework 7 | |
| 8 | Methods and Algorithms- Syntactic recognition, Finite-State-Machines, Push-Down-Automata | lecture 8 | homework 8 | |
| 9 | Methods and Algorithms- Search algorithms, Dynamic Programming, Dynamic Time Warping | lecture 9 | homework 9 | |
| 10 | Methods and Algorithms- Linear Prediction, Hidden Markov Models | lecture 10 | homework 10 | |
| 11 | Applications- Language Modeling | lecture 11 | homework 11 | |
| 12 | Applications- Machine Translation | lecture 12 | homework 12 | |
| 13 | Applications- Speech Enhancement | lecture 13 | homework 13 | |
| 14 | Applications- Speech Recognition | lecture 14 | homework 14 | |
| 15 | Applications- Speech Synthesis | lecture 15 | homework 15 | |