COURSE UNIT TITLE

: APPLICATIONS OF COMPUTATIONAL LINGUISTICS

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
DSM 5011 APPLICATIONS OF COMPUTATIONAL LINGUISTICS 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

Offered to

Data Science
Data Science (Non-Thesis-Evening)

Course Objective

To provide the students with theoretical and mostly applied study of; statistical or rule-based or machine learning-based modeling of natural languages, as well as the study of appropriate computational approaches to linguistic problems in data science. To establish practical knowledge of text processing, tagging, stemming, syntactic analysis, parsing and shallow parsing, semantic analysis, lexical resources, dictionaries and machine-readable dictionaries, anaphora resolution, word sense disambiguation, information retrieval and information extraction, document classification, spell checking, and web mining.

Learning Outcomes of the Course Unit

1   Implement and develop automated solutions for linguistic problems in companies or institutions.
2   Design and implement models for natural language processing, machine translation, and sentiment analysis.
3   Gain knowledge about statistical and machine learning models for computational linguistics.
4   Plan, manage and use different methodologies, procedures and techniques in natural language processing and text processing.
5   Participate in research projects in the area of computational linguistics and text mining.

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction. Basic concepts and terminologies in computational linguistics.
2 Applied linguistic systems Part 1. Regular expressions and automata, context free grammars and Chomsky normal forms, grammar checkers and spell checkers.
3 Applied linguistic systems Part 2. Parsers and shallow parsers, tokenizers, stemmers. Anaphora resolution. Syntactic analysis.
4 Statistical language modeling. N grams. Word2vec models: Skip gram and CBOW.
5 Computational and lexical semantics. WordNet. Word sense disambiguation. Sentiment analysis.
6 Topics in information retrieval Part 1. Search engines. Ranking and recommender systems in web mining.
7 Topics in information retrieval Part 2. Similarity metrics and document retrieval algorithms. LSA and LSI.
8 Statistical alignment and machine translation. Language translators. Question answering systems.
9 Text and document classification models and algorithms. Part 1.
10 Text and document classification models and algorithms. Part 2.
11 Clustering algorithms and models in text mining.
12 Social media and social network analysis.
13 Textual data visualization models, methods, and tools.
14 Project presentations. General discussion and review of the topics covered throughout the term.

Recomended or Required Reading

A. Clark, C. Fox, and S. Lappin, The Handbook of Computational Linguistics and Natural Language Processing, Wiley-Blackwell, 2013.

C. D. Manning, P. Raghavan, and H. Schütze, Introduction to Information Retrieval, Cambridge University Press, 2008.

C. D. Manning, and H. Schütze, Foundations of Statistical Natural Language Processing, MIT Press, 1999.

Planned Learning Activities and Teaching Methods

The course is taught in a lecture, class presentation, applied examples and exercises by using tools, and discussion format. Besides the taught lecture, group presentations are to be prepared by the groups assigned and presented in a discussion session. In some weeks of the course, results of the homework given previously are discussed.

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 MTE MIDTERM EXAM
2 ASG ASSIGNMENT
3 FIN FINAL EXAM
4 FCG FINAL COURSE GRADE MTE * 0.20 + ASG * 0.40 + FIN * 0.40
5 RST RESIT
6 FCGR FINAL COURSE GRADE (RESIT) MTE * 0.20 + ASG * 0.40 + RST * 0.40


Further Notes About Assessment Methods

None

Assessment Criteria

To be announced.

Language of Instruction

Turkish

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

mete.eminagaoglu@deu.edu.tr

Office Hours

Will be announced.

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 14 3 42
Preparations before/after weekly lectures 13 4 52
Preparation for final exam 1 20 20
Preparing assignments 2 30 60
Preparing presentations 2 12 24
Final 1 2 2
TOTAL WORKLOAD (hours) 200

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7
LO.13444335
LO.25434345
LO.34535444
LO.44544433
LO.53442424