SubjectsSubjects(version: 835)
Course, academic year 2018/2019
   Login via CAS
Competing in Machine Translation - NPFL101
Title in English: Soutěžní strojový překlad
Guaranteed by: Institute of Formal and Applied Linguistics (32-UFAL)
Faculty: Faculty of Mathematics and Physics
Actual: from 2018
Semester: winter
E-Credits: 3
Hours per week, examination: winter s.:0/2 C [hours/week]
Capacity: unlimited
Min. number of students: unlimited
State of the course: taught
Language: Czech, English
Teaching methods: full-time
Note: course can be enrolled in outside the study plan
enabled for web enrollment
Guarantor: RNDr. Ondřej Bojar, Ph.D.
Pre-requisite : NSWI095
Annotation -
Last update: Mgr. Barbora Vidová Hladká, Ph.D. (25.01.2018)

The seminar can serve as a supplement of Unix classes or a very practical introduction to some aspects of computational linguistics. We will collectively improve existing tools and systems for statistical machine translation, including neural machine translation, and take part in competitions like Our primary focus will be on Czech and English but other languages will be considered based on the interest of participants. Practically speaking, the seminar consists of scripting and operating a diverse collection of research tools and tackling a wide range of techn
Course completion requirements
Last update: Mgr. Barbora Vidová Hladká, Ph.D. (25.01.2018)

You can enroll into the NPFL101 seminar repeatedly, i.e. in more than one year.

Every year, the key requirement, for which you will receive the credit, is to submit a report describing your project for the seminar. Depending on your particular project, we may also agree on a presentation at the seminar, which then contributes the content to your report.

The report shall be at least 2-4 pages long and include proper introduction (the "big picture" of what your work is contributing to), technical details, as well as a standard conclusion. You can work on your project alone or in a small group, as agreed at the seminar.

If the resulting project leads to a workshop or a conference paper, there is no need to write a separate report.

The submission of the report is an iterative process, you send me a draft, and I will typically ask you for minor or greater revisions. We iterate, until the report is well written and rounded and I accept it. In this sense, the report can be "submitted" many times.

Literature -
Last update: Mgr. Barbora Vidová Hladká, Ph.D. (25.01.2018)

Bojar Ondřej, Chatterjee Rajen, Federmann Christian, Graham Yvette, Haddow Barry, Huang Shujian, Huck Matthias, Koehn Philipp, Liu Qun, Logacheva Varvara, Monz Christof, Negri Matteo, Post Matt, Rubino Raphael, Specia Lucia, Turchi Marco: Findings of the 2017 Conference on Machine Translation (WMT17). In: Proceedings of the Second Conference on Machine Translation, Volume 2: Shared Task Papers, Copyright © Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-945626-96-8, pp. 169-214, 2017.

Bojar Ondřej: Čeština a strojový překlad. Copyright © ÚFAL, Praha, Czechia, ISBN 978-80-904571-4-0, 168 pp., 2012.

Philipp Koehn: Statistical Machine Translation. Cambridge University Press. ISBN: 978-0521874151, 2009.

also including the chapter on neural MT:

Syllabus -
Last update: Mgr. Barbora Vidová Hladká, Ph.D. (25.01.2018)

At the seminar, we will improve machine translation systems (especially translation into Czech) and take part in the annual translation competitions like Our machines systems have repeatedly achieved relatively good results, and we won in the three consecutive years of 2013-2015, beating Google Translate among others.

Statistical machine translation is a challenging task especially in terms of the volume of data processed. It is quite common to work in parallel on dozens of computers, and can easily need 100 GB of disk and 100 GB of RAM for a single experiment. Neural machine translation then requires GPUs with at least 8 GB of RAM and training for days or weeks.

We will rely on existing tools that are implemented in a mixture of languages ​​such as Python, C/C++, Perl, Bash, and others. Very often, we will parallelize the calculations on the computing cluster of the department or MetaCentrum, including powerful graphics cards (GPUs).

During the semester, we will collectively improve open-source machine translation systems. People interested in natural language processing or deep learning will focus on analyzing or designing tricks and modifying models for better translation quality; general software engineers can focus on the infrastructure of the experimentation environment or the optimization of existing tools.

The seminar assumes only high school knowledge of the formal description of natural languages.

The seminar will take place at the Unix laboratory.

Charles University | Information system of Charles University |