I am wanting to use a character level CNN to classify a heap of documents based on the century which they are from. I am having difficulties finding any resources on how to do character level classification in WEKA and was wondering whether anyone has any experience with this. I am using the wekadeeplearning4j package but I can't seem to figure out how their CNN text iterator can work with characters instead of embeddings. I would greatly appreciate any help.



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.