on Nlp, Crawling, Youtube, Corpus, Social media, Python
Social Media are becoming less and less available for independent DS researchers. In 2020 Youtube still seems to be a small island of freedom. Thought APIs impose restrictions, we will go around all the prohibitions and crawl a small corpus for analysis. How? See my notes!
All ways to do it
on Nlp, Neurips, Deep learning, Neurips2019
Vancouver, Canada, December 8–14
NeurIPS conference is usually less populated by NLP people ¯_(ツ)_/¯
on Nlp, Spellchecking, Spelling correction
Spell checking is an essential part of many products and business applications. However, it’s working characteristics (speed, quality, memory consumption) are often not optimal - let’s see how to make your spell-checker fast and furious.
A quick intro
on Nlp, Keras, Deep learning, Text generation, Python
Patching frequent errors in text generation with Keras
Building a simple and nice text generator in Keras is not a difficult task, yet there are a few mistakes in the framework, that prevent you from succeeding.
on Nlp, Machine learning, Data, Open source, Russian
All projects for Russian with open source texts
During my work as an NLP-engineer, I always encountered a lot of corpus projects, that are not so publicly well-known and mentioned, yet they are a good source of text data for different kinds of research. Here I share this list with you, not forgetting to include more popular projects in it, of course, so that the list was complete.