NATURAL LANGUAGE PROCESSING AND COMPUTATIONAL TECHNIQUES
| Title | ΕΠΕΞΕΡΓΑΣΙΑ ΦΥΣΙΚΗΣ ΓΛΩΣΣΑΣ ΚΑΙ ΥΠΟΛΟΓΙΣΤΙΚΕΣ ΤΕΧΝΙΚΕΣ / NATURAL LANGUAGE PROCESSING AND COMPUTATIONAL TECHNIQUES |
| Code | Γλ4-442 |
| Faculty | Philosophy |
| School | English Language and Literature |
| Cycle / Level | 1st / Undergraduate, 2nd / Postgraduate |
| Teaching Period | Winter/Spring |
| Common | No |
| Status | Active |
| Course ID | 600023618 |
Programme of Study: 2024-2025
Registered students: 0
| Orientation | Attendance Type | Semester | Year | ECTS |
|---|---|---|---|---|
| KORMOS | Elective Courses | Winter/Spring | - | 6 |
| Academic Year | 2023 – 2024 |
| Class Period | Spring |
| Faculty Instructors | |
| Class ID | 600247835
|
Course Type 2021
Specific Foundation
Mode of Delivery
- Face to face
Digital Course Content
- e-Study Guide https://qa.auth.gr/en/class/1/600247835
Erasmus
The course is also offered to exchange programme students.
Language of Instruction
- English (Instruction, Examination)
Prerequisites
General Prerequisites
It is suggested that the students have already attended the module ΓΛ2-342 Introduction to Computational Linguistics.
Learning Outcomes
Upon completion of this course, students should be able to:
• understand basic concepts of Natural Language Processing.
• follow the current trends of an ever-evolving scientific area.
• recognize theoretical and applied linguistic theories in a technical environment.
• (computationally) analyze the English language (and literature) on different levels.
• acquire digital skills in language analysis and processing.
• interpret various phenomena by approaching them through machine learning and AI.
• get motivated to delve into the vast area of NLP.
General Competences
- Apply knowledge in practice
- Adapt to new situations
- Work autonomously
- Work in teams
- Generate new research ideas
Course Content (Syllabus)
The course "Natural Language Processing (NLP) and Computational Technologies" centers on the basic and fundamental concepts of the interdisciplinary area of Theoretical and Applied Linguistics, Computational Linguistics, Artificial Intelligence, and Cognitive Science. Its purpose is to cover a wide range of technical and advanced issues from Natural Language Generation, machine translation, dialogue systems and chatbots to semantic networks and machine learning. Significant topics from Theoretical Linguistics, Artificial Intelligence (AI) and even from Humanities and Social Sciences will be introduced through the dynamic and ever-changing prism of several state-of-the-art computing applications, breakthrough projects, theoretical frameworks, and dominant programming languages. This course will use a methodology of empirical linguistic analysis and processing of natural language that includes speech and language processing, machine learning, machine translation, language and knowledge representation, computational stylistics, and Digital Humanities.
In particular, the main aim of the course is to familiarize students with dominant and on-going research questions in this innovative and interdisciplinary area and to provide them access to several applications and projects, while at the same time familiarizing them to language and knowledge (en)coding. Moreover, we will also focus on how theoretical and applied linguistic theories are applied to the most up-to-date text processing techniques, language generation and knowledge representations of any Linguistics area. Theoretical and technical issues such as language models, neural networks, language generation, text encoding and annotation, ontologies, chatbots, information extraction will be supported by activities and assignments that will enable students to apply tools, data and algorithms.
Keywords
Natural Language Processing, Artificial Intelligence, Computational Linguistics, Digital Humanities
Educational Material Types
- Notes
- Slide presentations
- Interactive excersises
- Book
- Computational tools and applications • Python programming tutorial (mock lab)
Use of Information and Communication Technologies
Use of ICT
- Use of ICT in Course Teaching
- Use of ICT in Laboratory Teaching
- Use of ICT in Communication with Students
- Use of ICT in Student Assessment
Course Organization
| Activities | Workload | ECTS | Individual | Teamwork | Erasmus |
|---|---|---|---|---|---|
| Lectures | 27 | ||||
| Reading Assigment | 60 | ||||
| Interactive Teaching in Information Center | 12 | ||||
| Exams | 51 | ||||
| Other / Others | |||||
| Total | 150 |
Student Assessment
Description
(1.) 10% Participation
This interactive course blends the study of theoretical and applied subjects of Linguistics and Humanities with more technical and computational issues. This course is designed in an attempt to reflect this mix in the in-class/computer lab discussions and activities. This evaluation is directly dependent on active participation in the lectures and reading the weekly material.
(2.) 20 % Assignments (multiple-choices, quizzes, article reviewing)
There will be a group of assignments/ exercises that will be covered in their majority during each lecture of this course. Each activity will follow a significant subject (and related references), a discussion, a sample exercise and / or a small-range tutorial. Each type of exercise will be based on the quick and (often) direct evaluation of the students, as well as the preparation for corresponding exercises in the final examination.
(3.) 70% Exams
The final evaluation of the students is one final exam that will naturally draw on knowledge accumulated in the course up to that point and the main handbook; it will be roughly drafted around a similar format: a series of multiple choices and short-answer, identification questions, discussions, apps evaluation, and an essay question concerning specific computational issues and theories.
Student Assessment methods
- Written Exam with Multiple Choice Questions (Formative)
- Written Exam with Short Answer Questions (Formative)
- Written Exam with Extended Answer Questions (Formative)
- Performance / Staging (Formative)
- Written Exam with Problem Solving (Formative)
- Labortatory Assignment (Formative)
Bibliography
Additional bibliography for study
Coursebooks
Bird S., Klein E. & Loper E. (2009). Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O’ Reilly Media.
Jurafsky and Martin (2023). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition (3rd edition). Prentice Hall. (https://web.stanford.edu/~jurafsky/slp3/).
Supplementary Bibliography
Drucker, J. (2021). The Digital Humanities Coursebook: An Introduction to Digital Methods for Research and Scholarship. Routledge.
Martin, C. (2023). Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems. Amazon, Kindle edition.
Rothman, D. (2022). Transformers for Natural Language Processing: Build, train, and fine-tune deep neural network architectures for NLP with Python, Hugging Face, and OpenAI's GPT-3, ChatGPT, and GPT-4. O'Reilly Media.
Tunstall L., Von Werra L. & T. Wolf (2022). Natural Language Processing with Transformers, Revised Edition: Building Language Applications with Hugging Face. O'Reilly Media.
Last Update
01-02-2024
