All these things will be lost like tears in rain.
1 / 78
May 1, 19
May 1, 19
Feb 9, 17

Russian Open Speech To Text (STT/ASR) Dataset

4000 hours of STT data in Russian

Building end-to-end taxi hailing service automation

Almost, without STT for now

Complexity / generalization /computational cost in modern applied NLP for morphologically rich languages

Towards a new state of the art?

Spark in me - annual retrospective 2018

Spark in me - annual retrospective 2018

Winning a CFT 2018 spelling correction competition

Building a task-agnostic seq2seq pipeline on a challenging domain

Building client routing / semantic search and clustering arbitrary external corpuses at

And some applied benchmarks of sentence embedding methods

Parsing Common Crawl in 4 plain scripts in python

(alas not 2) =)

Parsing Common Crawl in 2 plain scripts in python

So easy! Really!

Parsing Wikipedia in 4 simple commands for plain NLP corpus retrieval


Training your own MNASNET

Or how we failed