Uppsala universitet  

Machine Translation, 7.5 HP / 5 HP, Autumn 2018

Course codes : 5LN426 (bachelor) 5LN711 (master; 7.5 hp) 5LN718 (master; 5hp)
Course coordinator: Sara Stymne
Course examiner: Mats Dahllöf
Teachers: Sara Stymne, Gongbo Tang, Zhengxian Gong, Eva Pettersson, Anna Sågvall Hein

News

  • 181003: The room for the second NMT lecture (2018-10-08, 10:00-12:00) has been changed to 16-0042! Not Blåsenhus!
  • 181002: The final seminars are now scheduled. Note that we will only use the schedule slots on November 5. The seminars on November 8 will be cancelled.
  • 181002: For bachelors and 7.5 master students: the deadline for lab 1 is extended, due to the closure of the student portal during the original deadline. The new deadline is October 9. The portal is supposed to be opened by then, but if you have problems submitting it through the portal, you can also email your lab report to Zhengxian.
  • 180924: A mid-term evaluation was held on September 24, during class. It is summarized here.
  • 180924: Note that the lecture on Thursday September 27 is cancelled
  • 180913: Detailed information about the projects is now available, see projects below.
  • 180813: The schedule should now be finalized, but there might still be some minor changes.
  • 180710: First version of the course web page is now online. Note that the information is still preliminary. Specifically, the schedule is still being updated!


More Information on

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


Schedule

Date
   Time   
Room
Type
 Content Teacher
Reading / Assignments
2018-09-04 10-12 7-0043 Lecture Introduction Sara Stymne Koehn Ch.1; JM 25.1-2; HS;
2018-09-05 14-16 7-0043 Lecture MT evaluation Sara Stymne Koehn Ch.8; JM 25.9
2018-09-06 9-12 Chomsky Lab Assignment 1: MT Evaluation Eva Pettersson Oral assessment in class
2018-09-10 12-14 16-0043 Lecture Introduction to SMT Sara Stymne Koehn Ch.2-4
2018-09-13 9-12 Chomsky Lab Assignment 2A: Word-based SMT - I Sara Stymne Oral assessment in class
2018-09-17 10-12 Geiger (6-1023) Lecture Alignment and Language Models Sara Stymne Koehn Ch.4, Ch.7
2018-09-17 13-16 Chomsky Lab Assignment 2B: Word-based SMT - II Sara Stymne Oral assessment in class
2018-09-19 13-15 Chomsky Lab Lab 1: Parallel corpora & alignment, 1 (ej 5LN718) Sara Stymne Lab report 1
2018-09-20 10-12 2-0076 Lecture Phrase-based SMT, Tuning Sara Stymne Koehn Ch.5
2018-09-24 10-12 2-0024 Lecture Decoding and more Sara Stymne Koehn Ch.6
2018-09-25 9-12 Chomsky Lab Assignment 3: Moses Sara Stymne Oral assessment in class
2018-09-26 13-15 Chomsky Lab Lab 1: Parallel corpora & alignment, 2 (ej 5LN718) Sara Stymne Lab report 1
2018-09-27 13-15 16-0043 Lecture CANCELLED (TBD / extra) Sara Stymne
2018-10-01 9-12 Chomsky Lab Assignment 4: Decoding Sara Stymne Oral assessment in class
2018-10-04 12-14 16-0043 Lecture Introduction to Neural Networks and NMT Gongbo Tang Koehn13, Further Reading
2018-10-08 10-12 12:128 (Blåsenhus) 16-0042 Lecture NMT 2 Gongbo Tang Koehn13, Further Reading
2018-10-11 13-15 Chomsky Lab Assignment 5: NMT Gongbo Tang Oral assessment in class
2018-10-15 10-12 16-2043 Lecture Guest lecture, rule-based MT Anna Sågvall-Hein
2018-10-15 13-15 Chomsky Lab Assignment 5: NMT Gongbo Tang Oral assessment in class
2018-11-05 10-12 6-K1031 Seminar Master projects I Gongbo, Zhengxian, Mats
2018-11-05 14-16 2-0024 Seminar Master projects II Gongbo, Zhengxian, Mats
2018-11-08 10-12 16-0041 Seminar Master projects III Gongbo Tang CANCELLED!
2018-11-08 14-16 6-K1031 Seminar Master projects IV Gongbo Tang CANCELLED!

Please observe that attendance is mandatory for the 7 assignment sessions and for the four seminars with project presentations.
If you cannot attend, please inform your teacher beforehand and we will find an alternative solution for you.

Literature

Most of the course is based on Koehn's introduction to Statistical Machine Translation.

Activities

There will be three types of activities during the course: assignments, labs and a project.
  • Assignments are lab-style exercises, that will be examined orally during class time. Attendance for assignment sessions is mandatory. There will be 6 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. There will be 1 lab (not for 5LN718).
  • A group project on some aspect of MT. The group project will be presented both orally during mandatory seminars and in a written report.
Both labs and assignments should be done in groups of two students. It is not necessary to work in the same pairs for all different assignments and labs. It is up to students to find a lab partner, and to form pairs to work in. You may not work on your own, and hand in labs/solve assignments on your own, unless there are special circumstances, and you have agreed on this beforehand with your teacher.

Assignments

There will be 6 assignments during the course, see below. The first assignments will be performed and examined during a 3-hour session each, and assignment 5 during two 2-hour sessions. To pass an assignment, it is mandatory to be present during the full session, to actively perform the tasks given, and to be prepared to discuss your results and experiences in class. Please read through the instructions for each assignment before the session, in order to use the classroom time in the best way possible! If someone fails to attend an assignment session, you should make up for this by solving the task on your own, and prepare a short written report. The deadline for handing in such a report is October 26. Such a report could be written individually or in pairs. The assignments should be performed in pairs of students. The pairs can be formed during the session, and you do not have to work in the same pair each session.

Assignment Theme Date
Assignment 1 Evaluation September 6
Assignment 2a Word-based SMT - I September 13
Assignment 2b Word-based SMT - II September 17
Assignment 3 Moses September 25
Assignment 4 Document-wide decoding October 1
Assignment 5 NMT October 11 and 15

Labs

There will be one lab, for which you are required to hand in a written lab report. This lab is only for 5LN426 and 5LN711, not for 5LN718 (master 5hp). Detailed instructions are available here. Note that the second part is different for master and bachelor students! There are two deadlines for the lab. The standard deadline, which is recommeded is October 9. If you fail to meet this deadline, there will be a second opportunity on November 9. The report should be written in English, and handed in through studentportalen.

Project

There will be a practical group project for all students, where you will perform MT experiments in practice. You will work in groups of 3-4 students. We will put together the groups, based on your wishes for which topics you prefer to work on. The list of topic suggestions wil be announced in good time before the choice. You can hand in your preferences by email to Sara, by September 24 at the latest. Give a list of at least three different topics you would like to work on, and rank them. We will try our best to accomodate everyone's wishes, but we cannot guarantee that you will get any of your prefered topics. If you fail to hand in a wish by September 24, you will be assigned arbitrarily to a topic and group.

The grade for the course will be dependent on your project grade. There will be a joint grade (VG/G/U) for all members of the group, based on the written group report, which will be the basis for your course grade. You will also get a grade (VG/G/U) on your individual reflection report, which can then individually increase (or decrease) your course grade, together with your part of the oral project presentation(s), and your individual contribution to the project work/report.

All reports are to be written in English and are due November 9 via Studentportalen in pdf format. If you for some reason fail to hand in either your project report, or individual report then, there will be a second chance on December 7.

Deadlines

Activity First deadline Second deadline
Project topic selction September 24 -
Assignment 1 September 6 October 26
Assignment 2 - I September 13 October 26
Assignment 2 - II September 17 October 26
Assignment 3 September 25 October 26
Assignment 4 October 1 October 26
Assignment 5 October 11 and 15 October 26
Lab 1 October 9 November 9
Project presentation November 5 or 8 By agreement
Project report November 9 December 7
Individual reflection report November 9 December 7

For assignments the first deadline is for participation in the oral examination. The second deadline if you isntead need to write a report if you missed the session.

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 a project on a specific topic in MT in a group of 3-4 students. This includes practical group work resulting in a written group report, two joint seminar presentations and an individual reflection report.

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 a project on a specific topic in MT in a group of 3-4 students. This includes practical group work resulting in a written group report, a joint seminar presentation and an individual reflection report.

Examination for Bachelors (5LN426)

 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 a project on a specific topic in MT in a group of 3-4 students. This includes practical group work resulting in a written group report, a joint seminar presentation and an individual reflection report.