Guided tutorial on building a text classifier — Introduction As Data Scientists, we are familiar with standard python libraries used for building Machine Learning algorithms. There is a high chance you have used pandas, NumPy, sci-kit learn, TensorFlow, or PyTorch to build the models and then tools like Docker, Kubernetes, and big cloud providers to deploy and serve…

Case of evaluation of African languages — Introduction An improvement in the quality of Machine Translation systems in recent years has caused solutions and devices using them to become available to the everyday consumer. Many apps offer automatic translation of text, voice, or images, allowing a user to communicate or understand the language without knowing it. This…

Practical case study with code that you can run — Introduction If you have been working in Data Science and ML for a while you know that the models you have trained can perform very unexpectedly in a production environment. This is because the production data tends to be different from the closed train dataset you used to create the…

A slightly different ML competition and why you should participate — Introduction This article introduces an interesting ML competition that is available right now on CodaLab and you can participate until the end of this year (2022). Initially, it looks like a standard “Kaggle” style competition but let me tell you why I find it particularly interesting. Obviously besides the fact…

A case study with AliExpress and Toloka — Introduction E-commerce platforms such as Amazon, AliExpress, and Shopify allow users to upload items they would like to sell. Thousands of vendors use them to connect with potential consumers. But not everything can or should be sold there, and it’s the responsibility of the platforms to monitor what’s being sold…

A case study of enriching food dataset — Introduction It has been months ago when Toloka and ClearML met together to create this joint project. Our goal was to showcase to other ML practitioners how to first gather data and then version and manage data before it is fed to an ML model. We believe that following those…

What our experiments found and your chance to try the model out — Introduction Can you take a general ML model for sentiment analysis, adapt it to a specific domain, and come up with acceptable results? How much of a challenge is that? As it turns out, it’s doable with reasonable effort. The ML team at Toloka recently tweaked a general sentiment model…

And how can you get data for your NLP projects? — Introduction The ocean of data that is the world wide web grows exponentially every year. But the biggest contributor is so-called “unstructured data”. …

And how to become one… — Introdution: Data Evangelist — what? So let’s get started with what Data Evangelist actually means. Data Evangelist is a person who talks about the importance of data and technology by providing technical content in a form of blogs, tutorials, talks, videos, etc. The goal of this is to spread the…