Natural Language Processing (CSF429) 

Scope and Objectives

The intent of the course is to present a broad undergraduate/post-graduate level introduction to Natural Language Processing (NLP, a.k.a. computational linguistics), the study of computing systems that can process, understand, or communicate in human language. The primary focus of the course will be on understanding various NLP tasks as listed on the course syllabus, algorithms for effectively solving these problems, and methods for evaluating their performance.

This subject aims to achieve the following goals:

• To introduce students, the challenges of empirical methods for natural language processing (NLP) applications.

• To introduce basic mathematical models and methods used in NLP applications to formulate computational solutions.

• To provide students with the knowledge on designing procedures for natural language resource annotation and the use of related tools for text analysis and hands-on experience of using such tools.

• To introduce students research and development work in information retrieval, information extraction, and knowledge discovery using different natural language resources.

• To give students opportunities to sharpen their programming skills in neural networks (and deep learning) for computational linguistics applications.

Logistics

• Lectures: Mon/Wed 11 AM-12 PM and Thu 2 PM-3 PM in room 6103. 

• Lab sessions: Tues 4 PM-6 PM in room 6114.

• Office contact hours: Sat 12 PM to 1 PM. 

• WhatsApp group for students:

Please join the WhatsApp group by clicking the following link:

NLP CSF429 whatsapp group 

Prerequisites

• Programming in Python: All lab assignments will be in Python (using Numpy and Pytorch).

• Knowledge of probability and statistics, matrix/vector notation, and operations.

• Foundation of Machine Learning: This course involves formulating cost functions, computing derivatives, and applying gradient descent for optimization. Prior knowledge of machine learning and deep learning concepts will significantly ease comprehension and progress throughout the course. Hal Daumé’s in-progress A Course in Machine Learning offers an accessible introduction to key concepts. Reading the first five chapters provides a solid foundation 

Text and Reference Books

• T1: Jurafsky and Martin, SPEECH and LANGUAGE PROCESSING: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Second and Third Edition ,  Speech and Language Processing

• R1: Manning and Schütze, Foundations of Statistical Natural Language Processing, MIT Press. Cambridge, MA: May 1999.  Manning and Schutze 

• R3: Natural Language Toolkit. Bird and Loper, and other developers. Available for free at: –NLTK

Navigation Preview

• Course Plan→ Details of learning outcomes and topics to be covered.

• Course Material→ Lecture notes or Supplementary material

• Assignments→ Weekly lab assignments , Group Assignment 

• Announcements→ Announcements related to lectures, labs etc.