Undergraduate Course: Machine Translation (INFR11133)
|School||School of Informatics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 11 (Year 4 Undergraduate)
||Availability||Available to all students
|Summary||Google translate can instantly translates between any pair of over one hundred human languages like French and English. It and other translation systems translate by reading millions of words of already translated text and learning statistical models to translation new text. This course will show you how they work, and what work is still to be done. It focuses on the use of fundamental ideas from algorithms, machine learning, and linguistics, showing how they apply to a real and difficult problem in artificial intelligence.
This 20 credit course replaces Machine Translation (Level 11) (INFR11062) - 10 credit course.
* Statistical models of translation
- Probabilistic models
- Latent variable alignment models
- n-gram language models
- linear models
- neural models
* Learning and inference for translation models
- Maximum likelihood
- Expectation maximization
- Discriminative learning
- Stochastic methods
- Dynamic programming
- Approximate search
* Linguistic phenomena and their associated modelling problems
* Evaluation of machine translation systems
- By humans
- By machines
- Use in design of loss functions for learning algorithms
* Engineering concerns
- Efficient data structures
* History of machine translation
Entry Requirements (not applicable to Visiting Students)
|| It is RECOMMENDED that students have passed
Accelerated Natural Language Processing (INFR11125) OR
Foundations of Natural Language Processing (INFR09028)
|Prohibited Combinations|| Students MUST NOT also be taking
Machine Translation (Level 11) (INFR11062)
||Other requirements|| This course is open to all Informatics students including those on joint degrees. For external students where this course is not listed in your DPT, please seek special permission from the course organiser.
Advanced Natural Language Processing or equivalent.
Students are expected to understand the following topics, or be prepared to learn them independently.
- Discrete mathematics: analysis of algorithms, dynamic programming, basic graph algorithms, finite and pushdown automata.
- Other essential maths: basic probability theory; basic calculus and linear algebra; ability to read and manipulate mathematical notation including sums, products, log, and exp.
- Programming: ability to read and modify python programs; ability to design and implement a function based on high-level description such as pseudocode or a precise mathematical statement of what the function computes.
- Linguistics: willingness to learn basic elements of linguistic description; no formal linguistics background required.
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Academic year 2017/18, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Lecture Hours 20,
Supervised Practical/Workshop/Studio Hours 4,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
||100% coursework: 4 assessments.
|No Exam Information
On completion of this course, the student will be able to:
- Understand the main linguistic challenges involved in machine translation.
- Understand state-of-the-art models and algorithms used to address challenges in machine translation.
- Design, implement, and apply modifications to state-of-the-art machine translation models algorithms.
- Understand the computational and engineering challenges that arise in the use of different models for machine translation.
- Understand, design and justify approaches to evaluation of machine translation systems.
|* Statistical Machine Translation, P. Koehn, Cambridge University Press, 2010|
* Primary literature
|Course organiser||Dr Adam Lopez
Tel: (0131 6)50 4430
|Course secretary||Mr Gregor Hall
Tel: (0131 6)50 5194