Keeping Up With Data #71

5 minutes for 5 hours’ worth of reading

Adam Votava
2 min readFeb 25, 2022
Source: Liu et al. (2021) via https://ruder.io/ml-highlights-2021/

It’s been a while since we last visited Prague. But we are here now and it always mean a busy week trying to see as many people as possible. That — logically — doesn’t leave too much time for reading, so just two items are on the reading list today.

  • ML and NLP Research Highlights of 2021: Following the advancements in NLP is hard, but Sebastian makes it much easier for everyone. This article covers fifteen topics and outlines what has happened, why is it important, and what next for each of them. There is also a list of 111 papers if you fancy a deep dive into any details. The topics I enjoyed the most? Efficient methods, program synthesis, and temporal adaptation. (Sebastian Ruder)
  • How the 2020 Mask Surge Reshaped Etsy’s Taxonomy Capabilities: Stable and robust taxonomies are valued by many businesses. Etsy is not an exception. But sometimes, the real-world context changes and must be reflected in the taxonomy quickly. Such as masks becoming mainstream back in 2020 called for a new category. And fast. It has taught Etsy to be “more responsive, in terms of both process and engineering capabilities.” A lot of data analysts and data scientists are working with taxonomies every day — think of financial transactions categorisation, or SKU categories. Remember: “the taxonomy must be able to reflect [the customers’] needs and desires.” Always. (Code as Craft)

What a week!

In case you missed the last week’s issue of Keeping up with data

Thanks for reading!

Please feel free to share your thoughts or reading tips in the comments.

Follow me on Medium, LinkedIn and Twitter.

--

--

Adam Votava

Data scientist | avid cyclist | amateur pianist (I'm sharing my personal opinion and experience, which should not to be considered professional advice)