ajyl

Creating Regression Tests for Multi-task Usecases

2

Hi, I am interested in generating regression tests for a multi-task learning scenario. While I am able to train or interact with the agents (ex: ```parlai dd -t task1,task2 ```),...

Bug in beam search of Expert

2

Hi all, Thank you for open sourcing this repository. I'm having trouble when decoding an expert model. In particular, all I did was clone the repo and run the following...

Hello, First off, thank you for releasing and maintaining your work, it's very clean and things are working nicely, I know it's a lot of work. I was just curious,...

Request for CBT Data

1

Hi, I am a PhD candidate at the University of Michigan - I was wondering if I could get access to the annotated data. The contact information/email addresses in the...

Hi, I noticed that the function call to `plot_interactions` in the [eval script](https://github.com/Pascalson/LERG/blob/main/eval.py#L74) includes a `save_path` argument, but the [definition](https://github.com/Pascalson/LERG/blob/main/lerg/visualize.py#L4) does not have this parameter. For now I've removed the...