COURSE UNIT TITLE

: NATURAL LANGUAGE PROCESSING

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
CSE 6015 NATURAL LANGUAGE PROCESSING ELECTIVE 3 0 0 8

Offered By

Graduate School of Natural and Applied Sciences

Level of Course Unit

Second Cycle Programmes (Master's Degree)

Course Coordinator

PROFESSOR DOCTOR YALÇIN ÇEBI

Offered to

COMPUTER ENGINEERING
Computer Engineering
Computer Engineering

Course Objective

Natural language processing, speech recognition and computational linguistics have begun to merge. The availability of very large on-line corpora has enabled statistical models of language at every level, from phonetics to discourse. It is important to show how language related algorithms and techniques can be applied to important real-world problems.

Learning Outcomes of the Course Unit

1   Recognize morphological analysis
2   Identify problems in speech analysis
3   Recognize probabilistic models
4   Analyze of grammars
5   Design a language model and evaluating language meaning models

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction
2 Regular Expression and Automata
3 Morphology and Finite State Transducers
4 Computational Phonology and Text-to Speech
5 Probabilistic Models of Pronunciation and Spelling
6 N-grams
7 HMMs and Speech Recognition
8 Word Classes and Part-of-Speech Tagging
9 Context-Free Grammars for English
10 Parsing with Context-Free Grammars
11 Features and Unificiation
12 Lexicalized and Probabilistic Parsing
13 Language and Complexity
14 Representing Meaning

Recomended or Required Reading

- Jurafsky, D., Martin, J.H., Speech and Language Processing, Prentice Hall, New Jersey, 2008, ISBN 978-0131873216
Supplementary Book(s):
- Manning, C.D., Schütze, H., Foundations of Statistical Natural Language Processing, The MIT Press, 1999, ISBN 978-0262133609
- Allen, J., Natural Language Understanding, Addison Wesley, 1994, ISBN 978 0805303346
Materials:
- AKTAŞ, Ö., ÇEBI, Y., Rule-Based Natural Language Processing Methods for Turkish, Lambert Academic Publishing (LAP), 2010, ISBN 978-3-8433-5599-5
- BIRANT, Ç.C., AKTAŞ, Ö., ÇEBI, Y., Root-Suffix Seperation of Turkish Words Basics,Design and Method, LAP Lambert Academic Publishing, 2010, ISBN 978-3-8433-5068-6
- AKTAŞ, Ö., ÇEBI, Y., Root and Suffixes Determination to Generate Large Scale Turkish Corpus - Basics, Concepts, Methods, LAP Lambert Academic Publishing, 2010, ISBN 978-3-8383-9423-7,(2010)

Planned Learning Activities and Teaching Methods

- Lectures
- Group study
- Application Development
- Presentation
- Homeworks
- Term project

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 RPT REPORT
2 CAS CASE STUDY
3 FIN FINAL EXAM
4 FCG FINAL COURSE GRADE RPT *0.30 + CAS *0.30 +FIN *0.40
5 RST RESIT
6 FCGR FINAL COURSE GRADE (RESIT) RPT *0.30 + CAS *0.30 +RST *0.40


*** Resit Exam is Not Administered in Institutions Where Resit is not Applicable.

Further Notes About Assessment Methods

There will be minimum 2 mid-term projects, averaged out grades for which will be 60% of the overall success of the students. One Term Project submitted at the end of the semester will have a weight of 40% of the resulting grade.

Assessment Criteria

Course outcomes will be evaluated with the projects prepared by the student.

Language of Instruction

English

Course Policies and Rules

Students are expected to attend courses and realize their presentations on time.

Contact Details for the Lecturer(s)

Prof.Dr. Yalçın ÇEBI
Dokuz Eylul University
Department of Computer Engineering
Tinaztepe Campus 35160 BUCA/IZMIR
Tel: +90 (232) 301 74 07
e-mail: yalcin@cs.deu.edu.tr

Office Hours

To be announced.

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 14 3 42
Preparing presentations 4 5 20
Preparations before/after weekly lectures 14 5 70
Preparing assignments 4 15 60
TOTAL WORKLOAD (hours) 192

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10PO.11
LO.132513355225
LO.255523555255
LO.355524555255
LO.455525555254
LO.543345555344