Top all-time · #11236
Sachin Joglekar
Personal blog · codesachin.wordpress.comaidata
Sachin Joglekar's personal blog at codesachin.wordpress.com covers ai and data. Since 2015, 7 different Hacker News readers have linked it 8 times, most often “Understanding the new Google Translate”. The last post was in 2017, but the archive is still widely read.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
One HN commenter cites this blog as a source on how Google's neural machine translation (GNMT) handles language pairs it was not directly trained on, such as Japanese to Korean.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Programming | Python | ML
Most-linked posts?
- Understanding the new Google Translate2 people · 2 mentions · first linked 2017-01-19
What Hacker News says?
> Do you have a source that that is actually what is happening behind the scenes? Indirectly yes, I do: https://codesachin.wordpress.com/2017/01/18/understanding-th... > What this basically means is: If during training you provide it examples of English->Japanese & English->Korean translations, GNMT automatically does Japanese->Korean reasonably well! In fact, this is the biggest achievement of GNMT as a project. It…
Comment linking /2017/01/18/understanding-the-new-google-translate/
on “Does Machine Translation Affect International Trade?”Submitted Self-Organizing Maps with Google’s TensorFlow as a story · 4 points
HN discussionSubmitted Non-Mathematical Feature Engineering Techniques for Data Science as a story · 3 points
HN discussionSubmitted K-Means Clustering with TensorFlow as a story · 3 points
HN discussionSubmitted How Neural Networks Generate Visual Art from Inspiration as a story · 2 points
HN discussionSubmitted Understanding the new Google Translate as a story · 2 points
HN discussionSubmitted A (small) introduction to Boosting as a story · 2 points
HN discussionSubmitted On the Bias Variance tradeoff in machine learning as a story · 1 points
HN discussion