Timo Schick

Sure, this is relatively straightforward. You can start from any of the examples found [here](https://huggingface.co/transformers/), or you can use any other script that uses HuggingFace's Transformers for any downstream task....

Hi @rajicon, you can find the script we've used for calculating the scores below. It's not exactly beautifully written but I hope it answers your questions. If it does not,...

Hi @suolyer, this is because in prompting work, WSC is typically framed as a generative task. That is, instead of classifying whether a (pronoun, entity) pair is correct, the entity...

> From my point of view, this is what has been happening so far, for an example that was handled by add_metadata_and_chunk_examples: [...] Yes, that's exactly what happens with the...

Hi @SaulLu, as discussed yesterday, I fully agree that this is an important issue that needs to be fixed. However, I'm not sure I fully understand how your proposed solution...