CENG0046 Text Vectorization

6 ECTS - 3-0 Duration (T+A)- . Semester- 3 National Credit

Information

Code CENG0046
Name Text Vectorization
Term 2024-2025 Academic Year
Term Spring
Duration (T+A) 3-0 (T-A) (17 Week)
ECTS 6 ECTS
National Credit 3 National Credit
Teaching Language İngilizce
Level Doktora Dersi
Type Normal
Mode of study Yüz Yüze Öğretim
Catalog Information Coordinator
Course Instructor
1


Course Goal / Objective

The student learns text vectorization methods that provide numerical representation of words, sentences and documents, increasing success in natural language processing problems based on deep learning. In this process, he learns to focus on the importance of context and low sparse computation methods.

Course Content

Vector Space Model and One-hot vectors, Sense Representation Problem and Synset Embedding, Sparsity Problem, Word Embedding Methods (Word2Vec, Glove, FastText), Contextualized Text Embeddings (BERT, ELMO, GPT-x), Synset Based Contextual Embedding (Generalized SemSpace)

Course Precondition

none

Resources

Son teknoloji makaleler

Notes

Daniel Jurafsky and James H. Martin, Speech and language processing an introduction to natural language processing, computational linguistics, and speech, 2000.


Course Learning Outcomes

Order Course Learning Outcomes
LO01 Learns the concepts of word and sense embeddings
LO02 Understands contextualization
LO03 Comments advantages of text representation
LO04 Implements state of the art methods to any text


Relation with Program Learning Outcome

Order Type Program Learning Outcomes Level
PLO01 Bilgi - Kuramsal, Olgusal On the basis of the competencies gained at the undergraduate level, it has an advanced level of knowledge and understanding that provides the basis for original studies in the field of Computer Engineering. 3
PLO02 Bilgi - Kuramsal, Olgusal By reaching scientific knowledge in the field of engineering, he/she reaches the knowledge in depth and depth, evaluates, interprets and applies the information. 3
PLO03 Yetkinlikler - Öğrenme Yetkinliği Being aware of the new and developing practices of his / her profession and examining and learning when necessary. 2
PLO04 Yetkinlikler - Öğrenme Yetkinliği Constructs engineering problems, develops methods to solve them and applies innovative methods in solutions. 4
PLO05 Yetkinlikler - Öğrenme Yetkinliği Designs and applies analytical, modeling and experimental based researches, analyzes and interprets complex situations encountered in this process.
PLO06 Yetkinlikler - Öğrenme Yetkinliği Develops new and / or original ideas and methods, develops innovative solutions in system, part or process design. 4
PLO07 Beceriler - Bilişsel, Uygulamalı Has the skills of learning. 3
PLO08 Beceriler - Bilişsel, Uygulamalı Being aware of new and emerging applications of Computer Engineering examines and learns them if necessary. 2
PLO09 Beceriler - Bilişsel, Uygulamalı Transmits the processes and results of their studies in written or oral form in the national and international environments outside or outside the field of Computer Engineering. 3
PLO10 Beceriler - Bilişsel, Uygulamalı Has comprehensive knowledge about current techniques and methods and their limitations in Computer Engineering. 4
PLO11 Beceriler - Bilişsel, Uygulamalı Uses information and communication technologies at an advanced level interactively with computer software required by Computer Engineering. 4
PLO12 Bilgi - Kuramsal, Olgusal Observes social, scientific and ethical values in all professional activities.


Week Plan

Week Topic Preparation Methods
1 Vector Space Model Reading paper Öğretim Yöntemleri:
Anlatım
2 One-hot vectors Reading paper Öğretim Yöntemleri:
Anlatım
3 Word-Sense Representation Problem Reading paper Öğretim Yöntemleri:
Anlatım
4 Word-Synset Embedding Reading paper Öğretim Yöntemleri:
Anlatım
5 Sparsity Problem Reading paper Öğretim Yöntemleri:
Anlatım
6 Word Embedding Apps (Word2Vec, Glove, FastText) Reading paper Öğretim Yöntemleri:
Deney / Laboratuvar
7 Contextualized Text Embeddings Reading paper Öğretim Yöntemleri:
Anlatım
8 Mid-Term Exam Study to all lecture notes Ölçme Yöntemleri:
Yazılı Sınav
9 Contextualized Apps (BERT, ELMO, GPT-x) Reading paper Öğretim Yöntemleri:
Deney / Laboratuvar
10 Synset Based Contextual Embedding (Generalized SemSpace) Reading paper Öğretim Yöntemleri:
Anlatım
11 Projects 1 Prepare project Ölçme Yöntemleri:
Proje / Tasarım
12 Projects 2 Prepare project Ölçme Yöntemleri:
Proje / Tasarım
13 Projects 3 Prepare project Ölçme Yöntemleri:
Proje / Tasarım
14 Projects 4 Prepare project Ölçme Yöntemleri:
Proje / Tasarım
15 Projects 5 Prepare project Ölçme Yöntemleri:
Proje / Tasarım
16 Term Exams Study to all lecture notes Ölçme Yöntemleri:
Yazılı Sınav
17 Term Exams Study to all lecture notes Ölçme Yöntemleri:
Yazılı Sınav


Student Workload - ECTS

Works Number Time (Hour) Workload (Hour)
Course Related Works
Class Time (Exam weeks are excluded) 14 3 42
Out of Class Study (Preliminary Work, Practice) 14 2 28
Assesment Related Works
Homeworks, Projects, Others 3 15 45
Mid-term Exams (Written, Oral, etc.) 1 15 15
Final Exam 1 15 15
Total Workload (Hour) 145
Total Workload / 25 (h) 5,80
ECTS 6 ECTS

Update Time: 24.05.2024 05:00