COMPUTATIONAL LINGUISTICS
| Title | ΥΠΟΛΟΓΙΣΤΙΚΗ ΓΛΩΣΣΟΛΟΓΙΑ / COMPUTATIONAL LINGUISTICS |
| Title in German | Computerlinguistik |
| Code | ΑΚ0264 |
| Faculty | Philosophy |
| School | German Language and Literature |
| Cycle / Level | 1st / Undergraduate |
| Teaching Period | Winter/Spring |
| Common | Yes |
| Status | Active |
| Course ID | 600024556 |
Programme of Study: PPS Tmīmatos Germanikīs Glṓssas kai Filologías (2020-sīmera)
Registered students: 45
| Orientation | Attendance Type | Semester | Year | ECTS |
|---|---|---|---|---|
| KORMOS | EPILEGOMENA EIDIKEUSĪS | Winter | - | 6 |
| Academic Year | 2024 – 2025 |
| Class Period | Winter |
| Faculty Instructors |
|
| Weekly Hours | 2 |
| Total Hours | 26 |
| Class ID | 600253352
|
Course Type 2021
Specialization / Direction
Mode of Delivery
- Face to face
Digital Course Content
- e-Study Guide https://qa.auth.gr/en/class/1/600253352
Language of Instruction
- Greek (Instruction, Examination)
Prerequisites
General Prerequisites
General Linguistics (Morphology, Syntax, Semantics)
Learning Outcomes
Upon successful completion of the course, students should:
understand the basic concepts of Computational Linguistics,
become familiar with techniques and methods of natural language processing,
learn about the latest advances in the area (i.e., Large Language Models),
become aware of the ethical and legal issues
understand the Architecture of mainstream Natural Language Processing tools in order to use them efficiently,
be able to participate in the design, development and evaluation of Natural Language Processing tools,
be able able to participate in the design, development, and evaluation of datasets following annotation guidelines and standards to ensure reproducibility of their effort.
General Competences
- Apply knowledge in practice
- Retrieve, analyse and synthesise data and information, with the use of necessary technologies
- Adapt to new situations
- Make decisions
- Work autonomously
- Work in teams
- Work in an international context
- Work in an interdisciplinary team
- Generate new research ideas
- Appreciate diversity and multiculturality
- Be critical and self-critical
- Advance free, creative and causative thinking
Course Content (Syllabus)
This is an introductory course in the inter-disciplinary field of Computational Linguistics and Natural Language Processing. The course is structured as follows:
1. Language Technology, Computational Linguistics, and Natural Language Processing (NLP): Basic concepts and principles.
2. A brief historical overview and significant milestones. Methods in NLP: from rule-based systems to probabilistic approaches, Large Language Models, Generative Artificial Intelligence (AI), and Human-centered AI.
3. Computational Linguistics and linguistic theory: Levels of linguistic analysis. Basic pre-processing: Part-of-Speech taggong and lemmatization.
4. Sentence structure: syntactic analysis (Context-Free Grammars, Dependency Parsing).
5. Approaches to semantics: Lexical semantics. Argument structure and semantic role role labeling. Abstract Meaning Representation.
6. Computational Semantics: Inference, paraphrasing, simplification.
7. Coreference resolution.
8. Language resources: Corpora, lexica, and tools. Corpus annotation (principles, methods, and tools).
9. Applications: Machine Translation. Information extraction: identification of events and entities, entity linking.
10. Applications: Sentiment analysis, offensive language identification. Irony, humor, and argumentation.
11. Computational Linguistics: Legal and ethical issues.
12. Presentations.
Keywords
Natural Language Processing, Natural Language Understanding, (Generative) Artificial Intelligence, Language Resources, Corpus annotation
Educational Material Types
- Notes
- Slide presentations
- Multimedia
- Book
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
Course Organization
| Activities | Workload | ECTS | Individual | Teamwork | Erasmus |
|---|---|---|---|---|---|
| Lectures | 39 | 1.6 | ✓ | ||
| Laboratory Work | 25 | 1 | ✓ | ✓ | |
| Reading Assigment | 58 | 2.3 | ✓ | ✓ | |
| Written assigments | 25 | 1 | ✓ | ||
| Exams | 3 | 0.1 | ✓ | ||
| Total | 150 | 6 |
Student Assessment
Description
1. Active participation 10% (Homework, reading questions)
2. Project and oral presentation 30%
3. Exams 60%
Student Assessment methods
- Written Exam with Multiple Choice Questions (Summative)
- Written Exam with Short Answer Questions (Summative)
- Written Assignment (Summative)
- Performance / Staging (Formative)
- Labortatory Assignment (Formative)
Bibliography
Course Bibliography (Eudoxus)
Αλεξανδρή, Χριστίνα (2018) Υπολογιστική Γλωσσολογία-Linguistik und ihre Anwendungen in der Computerlinguistik. Εκδόσεις Παπασωτηρίου
Additional bibliography for study
Γιούλη, Π. (2024) Υπολογιστική Γλωσσολογία: Μέθοδοι και εφαρμογές. Από τις συμβολικές προσεγγίσεις στη Μηχανική Μάθηση και την Παραγωγική Τεχνητή Νοημοσύνη. Σημειώσεις μαθήματος.
Παναγιωτακόπουλος, Χ., Τσαλίδης, Χ., Γάκης, Π. και Κόκκινος, Θ. (2022). Υπολογιστική γλωσσολογία. Από τον προγραμματισμό μέχρι τη διδακτική πράξη. [Προπτυχιακό εγχειρίδιο]. Κάλλιπος, Ανοικτές Ακαδημαϊκές Εκδόσεις. https://dx.doi.org/10.57713/kallipos-127
Τάντος, Α., Μαρκαντωνάτου, Σ., Αναστασιάδη-Συμεωνίδη, Ά., Κυριακοπούλου, Π. (2015). Υπολογιστική γλωσσολογία. [ηλεκτρ. βιβλ.] Αθήνα: Σύνδεσμος Ελληνικών Ακαδημαϊκών Βιβλιοθηκών. http://hdl.handle.net/11419/2205 https://repository.kallipos.gr/handle/11419/2205
Jurafsky, D. and Martin, J. H. (2020-2021) Speech and Language Processing (3rd ed. draft) https://web.stanford.edu/~jurafsky/slp3/
Jacob Eisenstein. (2019). Natural Language Processing. MIT Press. https://cseweb.ucsd.edu/~nnakashole/teaching/eisenstein-nov18.pdf
Bender, Emily M. and Alex Lascarides. (2019). Linguistic Fundamentals for Natural Language Processing II: 100 Essentials from Semantics and Pragmatics. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers
Goldberg, Y. (2015). A Primer on Neural Network Models for Natural Language Processing. ArXiv, abs/1510.00726. https://www.semanticscholar.org/paper/A-Primer-on-Neural-Network-Models-for-Natural-Goldberg/56edaa1368ff4dfa45388e4be24fdfbded7d88a7
Last Update
14-02-2025
