Skip to main content
TR

INFORMATION RETRIEVAL FOR NATURAL LANGUAGE PROCESSING

Course
CMPE640 - INFORMATION RETRIEVAL FOR NATURAL LANGUAGE PROCESSING
Department
Computer Engineering - English - PhD
Course Type
Course
Status
Required
Language
English
Credit
3
ECTS
0
T+P+L
3 + 0 + 0
Course Coordinator(s)
-
Prerequisite
-
Keywords
-

Course Description

-

INFORMATION RETRIEVAL FOR NATURAL LANGUAGE PROCESSING

Evaluation Tools (Active Term)

No evaluation items have been defined.

Course outcomes

No course outcomes have been defined yet.

Course Syllabus

Week Topic
Week 1 Introduction - Information Retrieval (IR) and Natural Language Processing (NLP)
Week 2 IR data models; vector space model, probabilistic models, word2vec, GloVe, semantic and others
Week 3 IR Techniques
Week 4 IR Techniques Cont. and IR Evaluation Methods
Week 5 Semantic Web for data representation
Week 6 NLP Application Areas; text recognition, sentiment analysis, document clustering, question-answering
Week 7 Stemming, morphological, syntactic, semantic analysis, lemmitization, regular expressions
Week 8 Midterm week
Week 9 Neural Networks and Deep Learning for IR and NLP - Recent Trends
Week 10 Neural Networks, Convolutional Neural Networks
Week 11 Transformers, state of the art language model for NLP - BERT (Bidirectional Encoder Representations from Transformers)
Week 12 Attention Networks
Week 13 Graph Convolutional Networks
Week 14 Project presentations
Week 15 Final Exam Week

Reference Books & Course Materials

  1. 01 Information Retrieval Models, Springer.
  2. 02 Natural Language Processing with Phyton - Free eBook (https://www.nltk.org/book/)
  3. 03 Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (1st Edition) (e-book)
  4. 04 Deep Learning for Natural Language Processing, https://www.manning.com/books/deep-learning-for-natural-language-processing

Learning Outcomes

No learning outcomes have been defined.

Program Outcomes

No program outcomes have been defined.

Po-Lo Matrix

The PO-LO matrix has not been populated yet.