Obligatory 2 is published

The second obligatory assignment is now available in our GitHub repository. This assignment deals with the Word-in-Context (WiC) task: given a target word and two sentences containing it, determine how similar the word's meaning is in the two contexts.

The assignment is due March 20. It is mostly targeted at finetuning masked language models, which will be covered in the group session on March 4 (tomorrow).

Note that we will evaluate your submitted models on a held-out test set. After grading is done, we will publish a leaderboard of the best 3 teams in terms of their models' performance. These 3 teams' members will get one extra point to their grades (unless they are already at the maximum points for this assignment).

Good luck!