Introducing students to the linguistic knowledge of natural languages together with the algorithms and technologies for processing them. Key linguistic concepts of words, morphology, parts-of-speech, syntax and semantics are presented together with algorithms and technologies like regular expressions, finite automata, context-free grammars, unification, first-order logic, lambda-notations, hidden Markov models as well as other rule-based or statistical algorithms.

Students, on completion of the course, would be able to

1. Apply knowledge on regular expression, part-of-speech to develop algorithms for spell checkers in text editors.
2. Apply knowledge on regular expression, part-of-speech and parsing to develop parsers for different natural language applications.
3. Develop algorithms for reasoning in natural language by translating the respective domain language into formal language like first-order logics.
4. Develop algorithms for information extractions from natural language texts.
5. Develop algorithms for Querying-Answering and Dialogue systems in natural language.

None.

I          Introduction to the ambiguity of natural language.

II          Words

1. Morphology and Parts of Speech
2. Algorithms: Regular Expression, Finite Automata, Hidden Markov Models
3. Language Models: N-Grams

III         Syntax

1. Context-Free Grammars
2.   Formal Grammars of English
3.       Syntactic Parsin
4.   Statistical Parsing                         
5.   Features and Unification                           

IV         Semantics

1. Lexical Semantics
2. Sentence Semantics
3. Discourse

None.

No designated textbooks, but lecture notes will be provided.

E.M. Bender and A. Lascarides, Linguistic Fundamental for Natural Language Processing: 100

Essentials from Semantics and Pragmatics, Morgan & Claypool Publishers, 2019

1. Vajjala and B. Majumder, Practical natural Language Processing, O'Reilly, 2020
2. Jurafsky, J. M. Martin, Speech and Language Processing, Second Edition, Pearson International, 2008
3. M. Nugues, Language Processing with Perl and Prolog, Second Edition, Springer Verlag, 2014
4. Carnie, Syntax: A Generative Introduction, Third Edition, Wiley-Blackwell, 2013
5. Steedman, The Syntactic Process, MIT press, 2001
6. Steedman, Surface Structure and Interpretation, MIT press, 1996
7. Bramer, Logic Programming with Prolog, Second edition, Springer Verlag, 2013
8. Blackburn, J. Bos, Representation and Inference for Natural Language, CSLI Publication, 2008

The Journal of Artificial Intelligence, Elsevier Science

Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), IJCAI Organization

Proceedings of Conferences of Associations for Advancement of Artificial Intelligence (AAAI), AAAI Organization

• Lectures: 45 hours.
• Self study: 100 hours.
• Homework: 10 hours.
• Project work: 25 hours.

1. Lectures
2. Homework: Several homework exercises requiring students to apply the knowledge acquired from lecture and discussion will be assigned and graded.
3. Project: Students will propose and execute a plan for a significant natural language understanding project in groups. Students should execute their projects independently under the guidance of the instructor and make a formal presentation of the results.

The final grade will be from the following constituent parts:

1. Midterm exam (20%)
2. Final exam (50%)
3. Assignments and project (30%)

Exams are open book.

A grade of “A” indicates excellent and insightful understanding of the key concepts and ability to implement sophisticated systems; “B” indicates a good understanding of the key concepts and ability to implement basic techniques; “C” indicates barely acceptable understanding and implementation ability; and “D” indicates poor understanding and implementation ability.