Undergraduate Course: Machine Translation (Level 10) (INFR10033)
|School||School of Informatics
||College||College of Science and Engineering
||Availability||Available to all students
|Credit level (Normal year taken)||SCQF Level 10 (Year 4 Undergraduate)
|Home subject area||Informatics
||Other subject area||None
||Taught in Gaelic?||No
|Course description||Machine Translation deals with computers translating human languages (for example, from Arabic to English). The field is now sufficiently mature that Google use it to allow millions of people to translate Web Documents each day. This course deals with all aspects of designing, building and evaluating a range of state-of-the-art translation systems. The systems covered are largely statistical and include: word-based, phrase-based, syntax-based and discriminative models. As well as exploring these systems, the course will cover practical aspects such as using very large training sets, evaluation and the open problem of whether linguistics can be useful for translation.
Information for Visiting Students
|Displayed in Visiting Students Prospectus?||Yes
Course Delivery Information
|Not being delivered|
Summary of Intended Learning Outcomes
|1 - Provide a written description of the main algorithms used in the system.
2 - Design and justify an approach to the evaluation of the system using state of the art tools and metrics
3 - Analyse the data collected by such an evaluation.
4 - Where the system is designed to deal with large volumes of data the student should also be able to describe how the system handles large data volumes and critically compare the system?s solution with other common solutions to the problem.
5 - Identify where linguistics knowledge is relevant in the design of the system and what influence of linguistic knowledge has on the translation quality and performance of the system.
|Written Examination 70|
Assessed Assignments 30
Oral Presentations 0
A single piece of coursework dealing with some practical aspect of translation. This will involve analysis of particular problems (for example, reordering or word selection), as well as actual problem solving. Typically, the problems set will not be research-level.
If delivered in semester 1, this course will have an option for semester 1 only visiting undergraduate students, providing assessment prior to the end of the calendar year.
||History of MT
* rule-based systems, ALPAC report, IBM models, phrase-based systems
* Factored Models
* Lexicalised reordering
* Changing the source
* Ngram models
* Scaling LMs (cluster-based LMs, Bloom Filter LMs)
* Knight on complexity, problem statement
* Stack decoding
* Human evaluation
* Automatic methods
* NIST competitions
* As factors
Parallel corpora etc (data)
* What they are, where they come from
* Comparable corpora
* Multi-parallel corpora
Relevant QAA Computing Curriculum Sections: Artificial Intelligence, Human-Computer Interaction (HCI), Natural Language Computing
||* Philipp Koehn: Statistical Machine Translation (forthcoming)
* Primary literature
Timetabled Laboratories 0
Non-timetabled assessed assignments 35
Private Study/Other 45
|Course organiser||Dr Mary Cryan
Tel: (0131 6)50 5153
|Course secretary||Miss Kate Farrow
Tel: (0131 6)50 2706