Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #25682

K

Kawin Ethayarajh

Personal blog · kawine.github.io/blogaidata

Kawin Ethayarajh's personal blog at kawine.github.io covers ai and data. Since 2021, 3 different Hacker News readers have linked it 3 times. No feed was found, so read it on the site itself.

No feed foundVisit the blog
3mentions?
3HN people?
2021–2025first – last linked?
Links on Hacker News per year · peak 1 in 2021

Too few sampled comments (3) to say how often HN recommends it.?

Why HN links it

HN readers link this NLP blog for posts on word analogies, embedding bias, and machine learning and language understanding. The comments only cite these posts, with no judgement of the writing.

Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Assistant Professor of Applied AI at UChicago Booth, working on behavior-bound machine learning

Most-linked posts?

  1. /blog/nlp/2019/06/21/word-analogies.html
    2 people · 2 mentions · first linked 2021-08-12

What Hacker News says?

  1. > 1. I'm thinking of it in terms of two different kinds of knowledge that we're going after when we try to (A) understand a proposition vs (B) make a probabilistic guess at the right answer from among a discrete range of possibilities. However our understanding of language works, it's not the same as flagging a maximized probability. If someone says "the bank is on Fifth Street next to the fire hydrant", you immedia…

    Comment linking /blog/nlp/2019/06/21/word-analogies.html

    on “Machine learning won't solve natural language understanding”
  2. We're already not far from being able to do something like... (Dean Martin "That's Amore") - (English) + (Hungarian) https://kawine.github.io/blog/nlp/2019/06/21/word-analogies....

    Comment linking /blog/nlp/2019/06/21/word-analogies.html

    on “How Translation Works, Book Title Edition”
  3. There's definitely associations embeded with words that we apparently have measurement systems for. It'd be really cool if someone familiar with what I'm linking to below could comment, especially regarding the word screech and its related forms! https://www.pnas.org/doi/10.1073/pnas.1720347115 https://github.com/chainsawriot/sweater https://kawine.github.io/blog/nlp/2019/09/23/bias.html

    Comment linking /blog/nlp/2019/09/23/bias.html

    on “Hundreds of changes made to latest editions of Roald Dahl's books”

Search all of HN for kawine.github.io