[WIP] ULMFiT for Text Classification

[ComputerMaestro]

Universal Language Model Fine-tuning for Text Classification. Here the model will be used for sentiment analysis as of now.

• [x] Files
• [x] Language Model
• [x] Binary Sentiment Analyzer
• [x] Docs
• [x] Tests
• [x] TextAnalysis.jl way (Documents)
• [x] Question classifier
• [ ] AG news

[ComputerMaestro]

@aviks did you upload the weights for which I gave the link?? if not I have different weights for Language model

[aviks]

I added the weights that were in the source in your PR

On Wed, Aug 21, 2019 at 9:40 AM Yash Patel notifications@github.com wrote:

@aviks https://github.com/aviks did you upload the weights for which I gave the link?? if not I have different weights for Language model

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/JuliaText/TextAnalysis.jl/pull/168?email_source=notifications&email_token=AAC4QJQU2Q76PC5724LHEH3QFT2KFA5CNFSM4IMPEZZKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD4Y2VRY#issuecomment-523348679, or mute the thread https://github.com/notifications/unsubscribe-auth/AAC4QJRIYW5KE4BDTXUOKZDQFT2KFANCNFSM4IMPEZZA .

[ComputerMaestro]

Can you please give me that link??

[aviks]

No actually, sorry, I was confused. I did not upload the weights for ULMFiT. Let me know when they are ready, and I will upload.

[ComputerMaestro]

https://drive.google.com/open?id=1Ki8XH_hkJc8qlqUBqMN8KyFYHcHcFo_N These are pretrained weights for ULMFiT Language model.

[ComputerMaestro]

https://drive.google.com/open?id=1lE3DiVs7RvesGVnu2LqqNEVmJ8QET3Tq @aviks , These are the weights for bin sentiment classifier with about 91% accuracy. Please upload these weights.

[ComputerMaestro]

@aviks I will test the model for the AG news dataset as well, and will let you know the results soon. Please let me know if there is something to change in the PR code.

[aviks]

@ComputerMaestro sorry for not looking at this for a while. Shall we get this finished up?

The pretrained weights are at https://github.com/JuliaText/TextAnalysis.jl/releases/download/v0.6.0/bin_sentiment_classifier_weights.bson.xz

Are all of Dhairya's feedback incorporated? (Except Zygote, we'll move to it later)

[ComputerMaestro]

@aviks , there seems to be a problem with implementing this now if we are using Flux 0.10.0 (latest). Since it supports Zygote . And the model I have made is based on Tracker . So it might break if we only put some changes to make it fit for current flux version. Can I make Flux less than or equal to 0.9.0 as a requirement??? For now till there is a zygote implementation

[aviks]

Updated version in #179