Logo

NYU NLP/Text-as-Data Speaker: Yonatan Belinkov (Technion), 10/8 - Shared screen with speaker view
Tal Linzen
19:28
Feel free to type questions into the chat; I’ll moderate them when Yonatan breaks to take questions.
Tal Linzen
31:55
(You can send your questions to “panelists and attendees” instead of just “panelists”, knowing what other people are planning to ask may be useful to other attendees)
Adina W
33:02
where do you get your prompts and how many do you use? Keita Kurita et al. (2019) have some that I think are better than most. For this sort of template project, my impression is that the choice of templates/word pairs is pretty important (from having done a few studies on this myself). How brittle are bias templates/word lists in your opinion?
Tal Linzen
41:15
Sorry, didn’t realize participants couldn’t unmute themselves
He He
54:22
Is this specific to certain heads or layers? For example, if we remove these layers/heads, I suppose then some other heads would have large indirect effect?
Tal Linzen
56:06
How should we interpret the y axis in the indirect effect plots? Is 0.05 big?
Giannis Karamanolakis
01:15:37
How do you choose hardcoded counterfactual values for the mediators when measuring direct/indirect effects? Is the choice inspired by how the mediator (e.g., attention head) works or is it random?
Giannis Karamanolakis
01:16:26
(sorry my internet connection is very bad)
Giannis Karamanolakis
01:17:46
thanks!
Adina W
01:29:08
thanks Yonaton, very neat stuff!