Introduction to Natural Languages Processing (MAE845)

General

School	School of Science
Academic Unit	Department of Mathematics
Level of Studies	Undergraduate
Course Code	MAE845
Semester	8
Course Title	Introduction to Natural Language Processing
Independent Teaching Activities	Lectures (Weekly Teaching Hours: 3, Credits: 6)
Course Type	Special Background
Prerequisite Courses	-
Language of Instruction and Examinations	Greek
Is the Course Offered to Erasmus Students	Yes (in English)
Course Website (URL)	http://nlampp-lab.uoi.gr/lab/

Learning Outcomes

Learning outcomes

The goal of this course is the deeper understanding of Natural Language Processing (NLP). During the course a detailed examination of the following topics are done: A historical retrospection of Language Technology evolution The goal of NLP and its Applications The NLP levels. Language Processors such as recognition machines, transducers, parsers and generators The language as a rule based system. Language Understanding as process NLP Resources for parsing, such as Data Base, Knowledge Base, Data Structure, Algorithms and Expert Systems Fundamental parsing strategies concerning context free grammars. Fundamental Methods of Computational Morphology, Computational Semantics and NLP. Implementations-Applications After completing the course the student can handle: theoretical documentation of problems solving exercises tracking applications which related to NLP different topics.

General Competences

Handle new problems Decision making Implementation- Consolidation

Syllabus

• A historical retrospection of Language Technology evolution
• The goal of NLP and its Applications
• The NLP levels. Language Processors such as recognition machines, transducers, parsers and generators
• The language as a rule based system. Language Understanding as process
• NLP Resources for parsing, such as Data Base, Knowledge Base, Data Structure, Algorithms and Expert Systems
• Fundamental parsing strategies concerning context free grammars.
• Fundamental Methods of Computational Morphology, Computational Semantics and NLP. Implementations-Applications

Teaching and Learning Methods - Evaluation

Delivery	Face-to-face, Distance learning, etc. Face to face
Use of Information and Communications Technology	- . Yes , Use of Natural Language and Mathematical Problems Processing Laboratory
Teaching Methods	Activity Semester Workload Lectures 39 Self study 78 Exercises 33 Course total 150
Student Performance Evaluation	Final test

Attached Bibliography

• Mitkov Ruslan, The Oxford Handbook of Computational Linguistics. ISBN 0-19-823882
• Jurafsky Daniel & Martin H. James, Speech and Language Processing - An Introduction to Ntural Language Proocessing, Computational Linguistics and Speech Recognition. ISBN 0-13-095069-6
• Allen James, Natural Language Understanding. ISBN 0-8053-0334-0,
• Natural Language Generation ed. by Gerard Kempen. ISBN 90-247-3558-0
• Professor's Notes.