Language Model Zoo 🦍

[cudawarped]

Hi Everyone,

I forgot to post to this thread a while back when I had a go with fastai v1 and ULMFit applied to Greek.

ULMFiT - Greek

Hi, I have been experimenting with ULMFiT for the Greek language using the standard fastai v1 features from lesson 3 without any bespoke processing. Language Model The Greek language model was pre-trained on a wikipedia dump of 57,956,630 tokens with a vocab of 26,952 words and resulting perplexity was 14.56 (notebook). Classification Task I could only find one recent SOTA NLP paper containing results on the Greek language - Building and evaluating resources for sentiment analysis in the Greek…

The results on the only “recent” Greek language NLP classification task I could find were better than those in the corresponding paper. I intend to update the code to include recent changes to the api and the forward and backward approach from the ULMFit paper.