Uppsala universitet  

Machine Translation, 7.5 HP / 5 HP, Autumn 2020

Course codes : 5LN711 (master; 7.5 hp) 5LN718 (master; 5hp)
Course coordinator and examiner: Sara Stymne
Teachers: Sara Stymne, Gongbo Tang

Syllabus: 5LN711, 5LN718

News

  • 201023: Note that there was an error on the schedule on this web page. All presentations will be on October 27 (as defined in all other information). A detailed schedule is now available.
  • 201001: Note: the supervision session on October 12 will be split into two sessions. Gongbo will run the October 12 session as planned, and Sara will be available on October 13, 10-12.
  • 200903: Note: the lecture on September 7 will be held only on Zoom!
  • 200901: Note: the lecture on September 2 will be held only on Zoom!
  • 200806: Course page under construction


More Information on

Literature
Activities
Examination for Masters (7.5 hp)
Examination for Masters (5 hp)


Schedule

Date
   Time   
Room
Type
 Content Teacher
Reading / Assignments
2020-08-31 10-12 Zoom (6-0022) Lecture Introduction Sara Stymne Koehn Ch.1; JM 25.1-2; HS
2020-09-02 15-17 Zoom only Lecture MT evaluation Sara Stymne Koehn Ch.8; JM 25.9
2020-09-03 15-16 Zoom Lab Assignment 1: MT Evaluation Sara Stymne 15.00-16.00 examination session on Zoom
2020-09-07 10-12 Zoom only Lecture Introduction to SMT Sara Stymne Koehn Ch. 2-4, 7
2020-09-09 10-12 Zoom (universitetshuset IV) Lecture Phrase-based SMT Sara Stymne Koehn Ch. 5-6
2020-09-10 15-16 Zoom Lab Assignment 2: Moses Sara Stymne 15.00-16.00 examination session on Zoom
2020-09-14 15-17 Zoom (7-0043) Lecture Introduction to NMT Gongbo Tang Koehn13 Ch.1-4; GB Ch.9
2020-09-16 13-15 Zoom (7-0043) Lecture Sequence to sequence models Gongbo Tang Koehn13 Ch.4-5, 7; Luong Ch.2.3
2020-09-17 15-16 Zoom Lab Assignment 3: Neural Language Models Gongbo Tang 15.00-16.00 examination session on Zoom
2020-09-21 13-15 Zoom (7.-0042) Lecture Advanced NMT Gongbo Tang Koehn13 Ch.5; Luong Ch.4-5
2020-09-22 14-15 Zoom Lab Assignment 4: seq2seq Gongbo Tang 14.00-15.00 examination session on Zoom
2020-09-23 15-17 Zoom (Universitetshuset IX) Lecture Advances and Challenges Gongbo Tang Koehn13 Ch.8; Tsinghua MT List
2020-09-24 10-13 Zoom (Chomsky) Lab Lab 1: Beam search decoding (Only 5LN711) Gongbo Tang Code and reports
2020-09-29 11-12 Zoom Lab Assignment 5: Transformer and Toolkit Gongbo Tang 11.00-12.00 examination session on Zoom
2020-10-05 13-15 Zoom and Chomsky Project supervision Gongbo, Sara
2020-10-12 13-15 Zoom and Chomsky Project supervision Gongbo
2020-10-13 10-12 Zoom Project supervision Sara
2020-10-19 13-15 Zoom and Chomsky Project supervision Gongbo, Sara
2020-10-27 9-12 Zoom Seminar Student presentations Gongbo, Sara Exact time subject to change
2020-10-27 13-16 Zoom Seminar Student presentations Gongbo, Sara Exact time subject to change

Please observe that attendance is mandatory for the assignment examination sessions and for the two final seminars (student presentations).
If you cannot attend, please inform your teacher beforehand and we will find an alternative solution for you.
The teaching mode for each session: online, campus, or combined will be announced in good time before each occasion.

Teaching mode, Covid-related information

Due to the Covid situation it will be possible to follow the course in an online format. Assignments will be examined during Zoom session. Lab sessions will be held only on Zoom (in a few cases we booked the lab room, in addition, and will also be available there). Help with the assignments will mainly be through the course forum in Studentportalen. Lectures will be held either online or in a mixed mode, with a possiblity to attend both online and on campus. The final seminars will be held either on Campus, in mixed mode, or online depending on the preference of students.

Please respect the current regulations and stay home if you are not feeling well, and maintain social distancing! Note that this also applies to teachers, so any Campus activities may be moved entirely online on short notice. Please always check your email before going to Campus! Note also that while we have booked large classrooms, there is a small risk that a classroom becomes full. In such an unlikely case, we will let students into the classroom on a first come, first served basis, and those arriving when the classroom is full can follow the activity on Zoom instead.

We ask you to turn your cameras on during all examination sessions on Zoom, i.e. during assignment sessions and seminars. Please also use your real names in Zoom, so that we know who is who!

This information will be continually updated throughout the term.

Literature

The course is based on Koehn's introduction to statistical MT, parts of Yoav Goldbergs book on neural networks for NLP, and other material as specified below. You will also be expected to find and read additional research articles online.

Additional reading:

Activities

The following activities are part of the examination
  • Assignments are lab-style exercises, which will be examined orally during class time (on Zoom). Attendance for assignment session discussions is mandatory. There are 5 assignments.
  • Labs are larger assignments for which a written lab report should be handed in. Supervision for labs are given during scheduled (non-mandatory) lab hours (on Zoom). There will be 1 lab (only for 5LN711, not for 5LN718).
  • A practical group project focusing on a low-resource language. The group project will be presented both orally during mandatory seminars and in a written report.
  • An individual report discussing your project and research literature for some specific topic, or an implementation.
  • An individual theoretical presentation based on your individual reports (only 5LN711).
Both labs and assignments can be done individually or in pairs of two students. It is not necessary to work in the same pairs for all different assignments and labs. It is up to students who wants to work in pairs to find a lab/assignment partner.

Assignments

There are 5 assignments during the course, see below for the content of each assignment. There is an oral examination for each assignment which will be held during a 1-hour Zoom session. Before this session you should have finished all tasks in the assignments, which should take roughly 2 hours for each assignment. Questions about the assignment can mainly be asked through the discussion forum in Studentportalen. The assignments can be performed in pairs of students or individually. You do not have to work in the same pair for each assignment.

If someone fails to attend an assignment examination session, you should make up for this by presenting the assignment to the teacher during one of the project supervision sessions (given that the teacher has time), or prepare a short written report. The deadline for handing in such a report is October 23. Such a report or presentation could be done individually or in pairs.

Assignment Theme Date
Assignment 1 Evaluation September 3
Assignment 2 SMT with Moses September 10
Assignment 3 Neural Language models September 17
Assignment 4 Sequence to sequence models September 22
Assignment 5 Transformer and Toolkits September 29

Labs

There will be one lab on beam search decoding in NMT, for which you are required to hand in a written lab report. This lab is only for 5LN711 (master 7.5hp), not for 5LN718 (master 5hp).

The lab can be performed individually or in pairs.

There is one supervised session for the lab on September 24 (both on Zoom and in Chomsky). Attendance is not obligatory, but recommended if you need help. You may also ask for help by email. Please use the forum only for general questions about the lab, not for sharing code, or discussing particular solutions.

Project

 There is a practical group project for all students, where you will perform MT experiments in practice. You will work in groups of 3-4 students, working on one language pairs focusing on translation for a low-resource language (translating from or into English). The languages will be announced in Studentportalen, and you will be able to sign up in a group working on a specific language. You may not pick a langauge that you know, or where you know a (closely) related language.

Each group should perform a project where you train and evaluate several MT systems for your language pair, linking your work to previous research on MT. The project should result in a joint project report and a joint seminar presentation.

Detailed information about the project is available here!

The project is graded. There will be a joint grade (VG/G/U) for all members of the group, based on the written group report and the presentation. Your grades for the full course will also depend on your personal contribution to the group work, see below.

The report should be written in English and are due October 30 via Studentportalen in pdf format.

Individual report/presentation

All students should write an individual report consisting of two parts: (1) a description and discussion of your individual contribution to the group project and (2) a discussion of one (5LN718) or more (5LN711) research articles.

Students in 5LN711 should also do a theoretical presentation, based on the articles discussed in your individual report.

Detailed information about the individual work is available here: 5LN711, 5LN718

You individual report (taken together with the individual presentation for 5LN711) will be graded (VG/G/U).

Deadlines

Activity First deadline Second deadline
Sign up for a project TBD -
Assignment 1 September 3 *
Assignment 2 September 10 *
Assignment 3 September 17 *
Assignment 4 September 22 *
Assignment 5 September 29 *
Individual topic/project choice (5LN711) October 14 --
Lab 1 (5LN711) October 14 November 13
Project presentation October 30 By agreement
Project report October 30 November 27
Theoretical presentation (5LN711) October 27 By agreement
Individual report October 30 November 27

* For assignments the first deadline is for participation in the oral examination. If you miss the session for an assignment, you need to do the assignment on your own, and either present it to the teacher during a project supervision session (given time), or hand in a written report at the latest October 23.

Examination for Masters (7.5 hp; 5LN711)

In order to pass the course, you have to:
  • Do the lab and pass the lab report. Lab reports will not be graded.
  • Do all assignments and pass the oral examination (or written report in case you fail to attend a session). Assignments will not be graded.
  • Perform an MT project in a group of 2-4 students. This includes practical group work resulting in a written group report and a joint seminar presentation.
  • Write an individual report and give a theoretical seminar presentation.

Grading

Passing all requiremnts in the course will earn you a G grade. In order to get a VG grade you need at least one VG on your individual work, or on the group work combined with a strong individual contribution to the group work (i.e. not doing a fair share of the project work will not grant you a VG, even if your group earns a VG).

Examination for Masters (5 hp; 5LN718)

 In order to pass the course, you have to:
  • Do all assignments and pass the oral examination (or written report in case you fail to attend a session). Assignments will not be graded.
  • Perform an MT project in a group of 2-4 students. This includes practical group work resulting in a written group report and a joint seminar presentation.
  • Write an individual report.

Grading

Passing all requirments in the course will earn you a G grade. To earn a higher grade you will either need to have a VG on the project, combined with a strong individual contribution to the group work (i.e. not doing a fair share of the project work will not grant you a VG, even if your group earns a VG), or have a strong individual contribution on a G project together with a VG on your individual report.