Electra w/Sequence classification?

[jondot]

I've been reading the code, but unsure if sequence classification is supported in some undocumented way with ELECTRA?

[guillaume-be]

Hello @jondot ,

You are correct this is currently missing. It is probably straightforward to add and I could publish an update, unless you would like to work on this?

[jondot]

I haven't yet studied the mechanics of implementing such a thing, I can't manage to keep up (just learned about ELECTRA's existence via a model I need to use), I'm wondering if this is something you can point some learning material for me and I'd have a high chances of success?

[jondot]

@guillaume-be from what I could study from the code, having a TokenClassifier already -- I would just copy it and change the copied structs and such to SequenceClassfier, the rest is again just copying around, there's no new logic that separates a Token and Sequence classifier other than the stuff in the pipeline. Inside the models it's all similar. So having that Electra has a token classifier, the job is already done for the sequence classifier. Is that a correct assumption?

[guillaume-be]

I would recommend checking a combination of the following resources:

• The Python implementation for ElectraForSequenceClassification. This shows you need to implement a ElectraClassificationHead submodule.
• A SequenceClassification model implementation in this crate such as DebertaV2ForSequenceClassification. This will give some high level guidance on how to create a new Struct with submodules as needed to reflect the Python implementation.

If you have a candidate model that is useful it would also be great to publish these weights and register them in the pretrained models -- this would allow adding a test for your implementation