2021

GPT-2 in Serbian

BERT in Serbian

The most advanced NLP language model is available in Serbian since yesterday. #thisisnotautogeneratedtext Context-aware, preserving learned semantic, and keeps track of the syntax. All in one in his only 87M parameters . Trained in a completely unsupervised manner. i.e. give-him-data-let-him-learn-by-himself. macedonizer/sr-roberta-base · Hugging Face ... Read More
GPT-2 in Macedonian

BERT in Macedonian

The most advanced NLP language model is available in Macedonian. #thisisnotautogeneratedtext The most advanced NLP language model is available in Macedonian, since yesterday. Context-aware, preserving learned semantic, and keeps track of the syntax. All in one in his only 87M parameters :-). Trained in a completely unsupervised manner. i.e. give-him-data-let-him-learn-by-himself. ... Read More
Pegasus for FinTech: autmatic text summarization for financial news

Pegasus 4 FinTech: This is BIG

I bet you spent a lot of time reading financial news, looking for the perfect shorting/longing stock. And, I bet that you don't have time enough to read all the data. And, this is 2021, and once again, HugginFace comes to save your time with his NLP models. Enjoy in financial texts summarization: three paragraphs in two short sentences. ... Read More
Data Science for Stock markets

Data Science for Stock market these days

We are living in an in intriguing time, for Data Science at least. We have Corona. No past data to train our models on whatsoever related. And social media increased the importance. Hard to train models for such circumstances. ... Read More
No-Code for Deep Learning: Ludwig

No-Code Just YAML -> Ludwig

Let's say you want something to achieve without making your hands dirty in a code. So, it would be best if you had no-code. From today's point of view, Ludwig would be your choice. ... Read More