Description of Individual Course Units
Course Unit CodeCourse Unit TitleType of Course UnitYear of StudySemesterNumber of ECTS Credits
9105056192007Natural Language ProcessingElective118
Level of Course Unit
Third Cycle
Objectives of the Course
This course is designed to provide students an understanding of the fundamental concepts and current research activities in the field of natural language processing (NLP). The students who have successfully completed the course, are anticipated to implement the NLP algorithms and develop new methods for the various problems in NLP.
Name of Lecturer(s)
Prof. Dr. Bahar Karaoğlan
Learning Outcomes
1Understanding of rule based and statistical natural language analysis methods.
2Understanding the application of Smoothing techniques.
3Gaining acquaintance with the current research and methods in the literature survey.
4Comprehension of syntactic and semantic analysis methods in NLP.
5Understanding the formation and use of corpora in NLP.
6Understanding the nature and use of language models: n-grams.
7Comprehension of Zipf’s Laws.
8Understanding the methods and applications of word tagging.
9Understanding the methods and applications of word stemming.
10Understanding the identification methods of collocations.
11Understanding machine translation.
Mode of Delivery
Face to Face
Prerequisites and co-requisities
None
Recommended Optional Programme Components
Knowledge of statistical concepts and familiarity with logic and probability
Course Contents
This course will cover various aspects of natural language processing. Topics include parsing algorithms, application of finite state methods to language processing tasks such as morphological analysis and morphological disambiguation statistical language processing, and applications such as machine translation, information extraction.
Weekly Detailed Course Contents
WeekTheoreticalPracticeLaboratory
1Introduction: Overview of NLP
2 Probability Introduction to probability theory--the backbone of modern natural language processing. Events, and counting. Joint and conditional probability, marginals, independence, Bayes rule, combining evidence. Examples of applications in natural language problem solving
3 Information Theory What is information? Measuring it in bits. The "noisy channel model." The "Shannon game"--motivated by language! Entropy, cross-entropy, information gain. Its application to some language phenomena problem solving
4 Information Theory (CONTİNUED) Zipf Law'sreading and discussion
5 Language Modelling and Naive Bayes Probabilistic language modeling and its applications. Markov models. N-grams. Estimating the probability of a word, and smoothing. Generative models of language. Their application: automatically determining the language problem solving
6 Information Extraction Information sources, rule-based methods reading and discussion
7 Syntax and Parsing for Context-Free Grammars (CFGs) Parsing, treebanks, attachment ambiguities. Contextfree grammars. Top-down and bottom-up parsing, empty constituents, left recursion, and repeated work. Probabilistic CFGs. research and reporting
8 Midterm
9 Part of Speech Tagging and Hidden Markov Models: The concept of parts-of-speech, examples, usage. The Penn Treebank and Brown Corpus. Probabilistic (weighted) finite state automata. Hidden Markov models (HMMs), definition and use
10 Maximum Entropy Models Identification methods of collocations.research and reporting
11 Computational Semantics: Semantic representations, lambda calculus, syntax/semantics interfaces, logical reasoningreading and discussion
12 Corpora and other resources
13 Machine Translation
14 Project Presentations
15 Project Presentations
16 Final
Recommended or Required Reading
Planned Learning Activities and Teaching Methods
Assessment Methods and Criteria
Term (or Year) Learning ActivitiesQuantityWeight
SUM0
End Of Term (or Year) Learning ActivitiesQuantityWeight
SUM0
SUM0
Language of Instruction
Turkish
Work Placement(s)
None
Workload Calculation
ActivitiesNumberTime (hours)Total Work Load (hours)
Midterm Examination133
Final Examination133
Attending Lectures14342
Problem Solving31030
Report Preparation21224
Project Preparation15050
Project Presentation2714
Individual Study for Mid term Examination12020
Individual Study for Final Examination13030
Reading3824
TOTAL WORKLOAD (hours)240
Contribution of Learning Outcomes to Programme Outcomes
PO
1
PO
2
PO
3
PO
4
PO
5
PO
6
PO
7
PO
8
PO
9
PO
10
PO
11
PO
12
PO
13
PO
14
PO
15
PO
16
PO
17
PO
18
PO
19
PO
20
PO
21
PO
22
PO
23
PO
24
LO1353    3       4   4    
LO253  3  3         2      
LO3   3       54   52   4  
LO45 3 3  4       2    4   
LO5     2           4      
LO64 4     55     2   2    
LO75 23           3   3    
LO853   3  4      2   2    
LO953   3  4      2   2    
LO1053   3  4      2   2    
LO115       4      3   3    
* Contribution Level : 1 Very low 2 Low 3 Medium 4 High 5 Very High
 
Ege University, Bornova - İzmir / TURKEY • Phone: +90 232 311 10 10 • e-mail: intrec@mail.ege.edu.tr