Skip to content

Not an issue, but I'm just curious :) #1

Description

@TheoSeo93

Hi ! I enjoyed reading your research paper on the Bert-based lexical substitution.
Can you confirm this code is the implementation of the paper?

One thing I'm very curious about is whether the BERT generates (you used the term "propose") substitute candidates that are semantically close to the target word (this is very interesting), by using "embedding dropout", and evaluates those candidates.

Am I right? If so, do you feed a masked sentence or just an original sentence without masking? Would there a reason not to use BertForMaskedLM, but just the Bert model?
Thank you and have a great day !
Cheers.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions