-
Notifications
You must be signed in to change notification settings - Fork 3
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add danFEVER #97
Add danFEVER #97
Conversation
for claim, evidence, label_id in zip(claims, evidences, labels): | ||
claim_is_supported = class_labels[label_id] == "Supported" | ||
|
||
sim = 1 if claim_is_supported else 0 # negative for refutes claims - is that what we want? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@Muennighoff - The DanFEVER dataset is similar to the FEVER dataset. Just wanted to make sure that this dataset is constructed fairly similar to FEVER.
I use the claim as the query to all the evidence segments as the corpus. The relevance score is then determined by whether the claim is supported.
However, I am unsure if assigning 0 to "not supported" and "not enough evidence" is meaningful.
What are your thoughts?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
However, I am unsure if assigning 0 to "not supported" and "not enough evidence" is meaningful.
If that's the same way it is done for FEVER, then I think it's okay!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I am unsure how it is done for FEVER (can I find the processing script somewhere?)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is what it says in BEIR, so it does seem like they everything that's not the evidence is a 0
FEVER [60] The Fact Extraction and VERification dataset is collected to facilitate the automatic fact checking. We utilize the original paper splits as queries Q and retrieve evidences from the pre-processed Wikipedia Abstracts (June 2017 dump) as our corpus T
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good, feel free to merge
Added danfever as a retrieval dataset
fixes #93