DIKI1007-NLP-for-Humanities

(Previously known as DIKI1003-NLP-for-Linguists)

Course description

The course is based on weekly teaching materials and exercises as well as an exam at the end of the course.

The course is a modified version of the MOOC by Tuomo Hiippala (Uni Helsinki). Some instructions may mention the MOOC - nevermind those.

Passing the course

The course consists of the weekly exercises, discussion on the discussion forum, and the exam (also done on CSC Notebooks). To do the exam, you need to have submitted all the weekly exercises. The evaluation is based on the weekly exercises and the exam with extra points from participating actively in the forum discussions.

Course Schedule

• The deadline for submitting the exercises is on Wednesdays at 23.59.
• Submitting the exercises late is possible until the next week's Monday, but you can only get 75% of the points if the submission is late.
• You need to get 20% of the weekly points to be able to move forward in the exercises

Teaching materials

The teaching materials are found at https://applied-language-technology.mooc.fi/html/index.html. Parts I and II belong to the previous course, part III to this one.

Interaction with other students and teacher

I strongly encourage discussing the exercises on the course discussion forum, available on the course Github page (link above). Very often, people face very similar challenges! You can also get extra points by actively participating - either with questions, answers or comments!

If you need more assistance than the discussion forum can offer you, you can contact the course teacher (veronika.laippala@utu.fi) by email. Office hours can be arranged if needed, but please use the discussion forum as your first option for help!

Course environment

The course happens on the platform CSC Notebooks, available at https://noppe.2.rahtiapp.fi/welcome.

To get to the** course environment,** please do the following steps:

1. Log in to the notebooks by signing in using your HAKA (that is UTU) -credentials
2. Find the correct course environment by writing the code dik-itvyxi98 to ”Join workspace”. After these two steps, you should see the course "DIKI1002/1003 Course Environment - 2025 version" in your "My workspaces".
3. Click on the starting icon on the right side of the course name box. This starts a session on the course server.
4. Once you have started a session, the course materials are listed under the directory "notebooks" on the left side of the screen.
5. Detailed instructions on how to use Notebooks can be found here: https://applied-language-technology.mooc.fi/html/getting_started.html

Exercises

**The exercises come to the Notebooks environment using the platform Test My Code. **

First, you need to create credentials to TMC at https://tmc.mooc.fi/.

Detailed instructions on how to use TMC can be found here: https://applied-language-technology.mooc.fi/html/tmc.html. Please read those.

A short video on how to log into CSC Notebooks and use TMC can be found here: https://drive.google.com/file/d/1NPuDcmd7ds1O2N3gknQaLkbgSFh-Agx9/view?usp=sharing (Finnish)

The steps to copy the exercises are:

1. Type the command tmc login on the terminal command line and press enter
2. Give your username and password (the password you type does not show, but it is still registered)
3. If the login is successful, TMC will prompt you to select an organization. Please select "Turun yliopisto".
4. Download the exercises by typing tmc download (and enter). Please select "ty-utu-nlp-for-linguists". (This is the old name of the course.)

Now, the exercise notebooks should show in the menu on left.

Submitting the exercises

Once you have done the exercise of the week, you can test how many points you get, and when happy with the result, submit your exercise. The testing is done with the command tmc test, and submission with tmc submit.

N.B.! the command tmc test evaluates your exercises locally, for you. Only the command tmc submit submits them to the course platform, where I can see them. Remember to submit!

Course schedule

The correct solutions are shown here on Github after the deadline.

---

Week 1

• part_01-stanza_basics
• Office hours Mon 24.3 at 10.00-10.30 at https://utu.zoom.us/j/62780466942
• Exercise dl Wed 26.3 23.59
• Submission possible with less points until Mon 31.3 23.59
• Correct answers:

Week 2

• part_02-universal_dependencies
• Office hours Mon 31.3 at 10.00-10.30 at https://utu.zoom.us/j/62780466942
• Exercise dl Wed 2.4 23.59
• Submission possible with less points until Mon 7.4 23.59
• Correct answers:

Week 3

• part_03-pattern_matching
• Office hours Mon 7.3 at 10.00-10.30 at https://utu.zoom.us/j/62780466942
• Exercise dl Wed 9.4 23.59
• Submission possible with less points until Mon 14.4 23.59
• Correct answers:

Week 4

• part_04-distributional_hypothesis
• Office hours Mon 14.3 at 10.00-10.30 at https://utu.zoom.us/j/62780466942
• Exercise dl Wed 16.4 23.59
• Submission possible with less points until Mon 21.4 23.59
• Correct answers:

Week 5

• part_05-word_embeddings
• No office hours because of Easter
• Exercise dl Wed 23.4 23.59
• Submission possible with less points until Mon 28.4 23.59
• Correct answers:

Week 6

• part_06-discourse
• Office hours Mon 28.4 at 10.00-10.30 at https://utu.zoom.us/j/62780466942
• Exercise dl Wed 30.4 23.59
• Submission possible with less points until Mon 5.5 23.59
• Correct answers:

Week 7 - Exam

• part_07-final_exam
• Open until 21.5

Viikko 8 - Grade my work

• part_08-grade_my_work
• Do this when you are happy with the exam result, so I know to add your grade to Peppi!
• Open until 21.5