How to reduce word embeddings models by 300 times, with almost the same performance on downstream NLP tasks — FastText is a method for encoding words as numeric vectors, developed in 2016 by Facebook. Pretrained fastText embeddings help in solving problems such as text classification or named entity recognition and are much faster and easier to maintain than deep neural networks such as BERT. …

Load embeddings only for the tokens of your language to reduce the model size — T5 is an encoder-decoder transformer from Google that once was SOTA on several NLU and NLG problems and is still very useful as a base for seq2seq tasks such as text summarization. The first T5 model was for English only, and then the massively multilingual version followed. …

If you don’t like and don’t understand math, does it mean you are stupid? Do you need to love math to achieve at finance/engineering/science? No. Where you possibly are People say that math is the queen of all sciences, that without mathematical thinking it’s impossible to survive and to strive, that everyone should be…

Recently I bumped into a question on Stackoverflow, how to recover phrases from abbreviations, e.g. turn “wtrbtl” into “water bottle”, and “bsktball” into “basketball”. The question had an additional complication: lack of comprehensive list of words. That means, we need an algorithm able to invent new likely words. I was…