PV061 Introduction to Machine Translation

Faculty of Informatics
Autumn 2019
Extent and Intensity
2/0/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
Teacher(s)
Mgr. et Mgr. Vít Baisa, Ph.D. (lecturer)
prof. PhDr. Karel Pala, CSc. (lecturer)
doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
Guaranteed by
doc. RNDr. Aleš Horák, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: prof. PhDr. Karel Pala, CSc.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics
Timetable
Mon 16:00–17:50 B411
Prerequisites
Recommended are courses PA153 and Logical programming I
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
fields of study / plans the course is directly associated with
Course objectives
The course offers the information about the basics of machine translation. The students will learn about: history of the Machine Translation (MT) and the state of art;
- approaches to MT: binary MT, interlingua based MT, techniques of translation memory using parallel corpora, statistical translation, factored translation and others;
- translation process: lexical analysis and machine dictionaries, morphological and syntactic analysis, representation of the sentence structure, transfer rules, semantic representation, synthesis;
- key issues of MT: ambiguity problem, knowledge representation, semantic issues, terminology;
The students will understand: - some successful MT systems: TAUM-METEO, TAUM-AVIATIC, EUROTRA, TRADOS, Dejavu, Rosetta, Google Translator, etc.;
- the existing systems working with Czech language - TRANSEN, PC-TRANSLATOR, Matrix;
- EU framework: projects like EuroMatrix, standardization, large parallel corpora, multipurpose and reusable resources;
- examples and experiments: small experimental translation system for Czech and English based on Prolog;
- machine translation and its relation to knowledge representation and Artificial Intelligence; - evaluation of the translation systems;
Learning outcomes
After the course, students will be able to:
- classify systems of machine translation and give examples;
- differentiate and characterize basic types of MT;
- define fundamental terms from MT field;
- enumerate language phenomena decreasing quality of MT;
- enumerate methods of automatic quality assessment of MT;
- enumerate language resources required for building MT systems;
Syllabus
  • History of the Machine Translation (MT) and the state of art;
  • Approaches to MT: binary MT, interlingua based MT, techniques of translation memory using parallel corpora, statistical translation, factored translation;
  • Translation process: lexical analysis and machine dictionaries, morphological and syntactic analysis and representation of sentence structure, transfer rules, semantic representation, synthesis;
  • Key issues of MT: ambiguity problem, knowledge representation, semantic issues, terminology;
  • MT with speech input and output (Verbmobil);
  • Some successful MT systems: TAUM-METEO, TAUM-AVIATIC, EUROTRA, TRADOS, Dejavu, Rosetta, Google Translator the existing systems working with Czech language - TRANSEN, PC-TRANSLATOR, Matrix;
  • EU framework: projects like EuroMatrix, standardization, large parallel corpora, multipurpose and reusable resources;
  • Examples and experiments: small experimental translation system in Prolog - Czech - English;
  • Evaluation of the translation systems;
  • Machine Translation and its relation to Artificial Intelligence;
Literature
  • HUTCHINS, W. John and Harold L. SOMERS. An introduction to machine translation. London: Academic Press, 1992, xxi, 362 s. ISBN 0-12-362830-X. info
Teaching methods
Teaching is performed in the form of oral lectures and seminars, in which the slides and demos of the relevant software tools are combined. Students work out homeworks, prepare presentations based on the literature they had read and develop smaller projects. At the appropriate points of the teaching the open dialog between a teacher and students is used.
Assessment methods
oral examination, written test
Language of instruction
Czech
Further Comments
Study Materials
The course is taught once in two years.
The course is also listed under the following terms Autumn 2002, Autumn 2003, Autumn 2004, Autumn 2005, Autumn 2006, Autumn 2007, Autumn 2008, Autumn 2009, Autumn 2010, Autumn 2011, Autumn 2012, Autumn 2015, Autumn 2017, Autumn 2021, Autumn 2022, Autumn 2023, Autumn 2024.
  • Enrolment Statistics (Autumn 2019, recent)
  • Permalink: https://is.muni.cz/course/fi/autumn2019/PV061