HackerNews Readings
40,000 HackerNews book recommendations identified using NLP and deep learning
[Top 10 as of 2021-09-21]
Thinking, Fast and Slow by Daniel Kahneman, Patrick Egan, et al.
The Pragmatic Programmer: 20th Anniversary Edition, 2nd Edition: Your Journey to Mastery by David Thomas, Andrew Hunt, et al.
Dune by Frank Herbert, Scott Brick, et al.
Snow Crash by Neal Stephenson, Jonathan Davis, et al.
The Selfish Gene by Richard Dawkins, Lalla Ward, et al.
Why We Sleep: Unlocking the Power of Sleep and Dreams by Matthew Walker, Steve West, et al.
The Design of Everyday Things: Revised and Expanded Edition Don Norman by Atlas Shrugged Ayn Rand
Brave New World by Aldous Huxley
Cryptonomicon by Neal Stephenson, William Dufris, et al.
Zen and the Art of Motorcycle Maintenance: An Inquiry Into Values by Robert M Pirsig
Show HN: 40k HN comments mentioning books, extracted using deep learning´ | Hacker News
tracyhenry [op]:
This book aggregation idea is not new. A bunch of sites have done similar things
Simply matching the names of the books would produce a whole lot of irrelevant results.
This is where Deep Learning comes into play.
fine-tune a BERT model on a couple thousand labeled HN comments and predict accurately whether each word in a comment is part of a book or not - a task commonly termed as Named Entity Recognition (NER).
unmole:
Interesting idea but not completely accurate. My own comment about how I hated Thinking, Fast and Slow seems to be counted as a recommendation.
Wow, the part about using deep learning for NER really stood out to me! As an AI enthusiast, seeing BERT finetuned for this is fascinating. It makes me wonder about the broader applications for content analysis. You always bring up such insightful methods. Have you considered training this model for other entity recognition tasks?