- CS-AD 220: Natural Language Processing. (Spring 2017, Spring 2016, Spring 2015†)
Undergraduate Computer Science Course. New York
University Abu Dhabi
Slides and Assignments *
The field of natural language processing (NLP), also known as
computational linguistics, is interested in the modeling and
processing of human ("natural") languages. Examples of some of the
advances of NLP include machine translation (as in Google Translate,
which translates among 80 languages) and question answering (as in
IBM’s Watson system, which won Jeopardy in 2011). This course covers
foundational NLP concepts and ideas, such as finite state methods,
n-gram modeling, hidden Markov models, part-of-speech tagging,
context free grammars, syntactic parsing and semantic
representations. The course will survey a range of NLP applications
such as information retrieval, summarization and machine
translation. Concepts taught in class will be reinforced in practice
by hands-on assignments.
†This course was taught as CS-AD 219 "Topics in Computer
Science: Natural Langauge Processing" in Spring 2015.
- COREI-AD 58: Words (Fall 2016, Fall 2015)
Undergraduate Core Course. New York
University Abu Dhabi
* Slides *
Words, words, words. How do words, as basic units of language, help us communicate our thoughts? How are they internally constructed? And how do they come together to form complex meanings? How are words from different languages similar, and how are they different? Do words reflect or shape our thought? Do they expand or constrain our imagination? This interdisciplinary course explores what words are and how we think of them by bringing together insights and ideas from a number of fields: linguistics, computer science, psychology, sociology, philosophy, history, literature, religion and visual arts to help answer these questions. Students will read materials from a variety of books and articles and discuss them in class, and they will engage in solving language puzzles. Students will learn how to analyze words in terms of their form, function and meaning in context. Class final group project will be to invent a constructed language.
- COMS E6998: Topics in Computer Science: Machine Translation. (Spring 2013, Fall 2011, Falll 2010)
Graduate Computer Science Course. Columbia University
* Syllabus *
This seminar course introduces students to research in Machine Translation.
- Habash, Nizar. Introduction to Arabic Natural Language Processing, Synthesis Lectures on Human Language Technologies, Graeme Hirst, editor. Morgan & Claypool Publishers. 187 pages, 2010. (PDF version from Publisher)
Description: This book provides system developers and researchers in natural language processing and computational linguistics with the necessary background information for working with the Arabic language. The goal is to introduce Arabic linguistic phenomena and review the state-of-the-art in Arabic processing. The book discusses Arabic script, phonology, orthography, morphology, syntax and semantics, with a final chapter on machine translation issues. The chapter sizes correspond more or less to what is linguistically distinctive about Arabic, with morphology getting the lion's share, followed by Arabic script. No previous knowledge of Arabic is needed. This book is designed for computer scientists and linguists alike. The focus of the book is on Modern Standard Arabic; however, notes on practical issues related to Arabic dialects and languages written in the Arabic script are presented in different chapters.
Table of Contents:
What is "Arabic"? / Arabic Script / Arabic Phonology and Orthography / Arabic Morphology / Computational Morphology Tasks / Arabic Syntax / A Note on Arabic Semantics / A Note on Arabic and Machine Translation
This book was translated to Arabic by Prof. Hend Al-Khalifa of King Saud University in Riyadh, Saudi Arabia (2014).
(King Saud University Press)
- Natural Language Processing of Arabic and its Dialects.
Mona Diab and Nizar Habash.
EMNLP 2014, NAACL 2012, MEDAR 2009, LREC 2008, NAACL 2007, AMTA 2006
(EMNLP 2014 Video and Slides)
- Introduction to Arabic Natural Language Processing.
MEDAR 2009, LREC 2006, ACL 2005, AMTA 2004
(MEDAR 2009 Slides)
(Old videos from a version given at Johns Hopkins University Summer Workshop in 2005: Part 1,
Part 2, and
- Arabic Natural Language Processing for Machine Translation.
AMTA 2012, AMTA 2008
(AMTA 2012 Slides)