HN Explorer

rspeer

↗ HN profile [ 78.0 ms ] full profile
Karma
5,317
Created
January 4, 2010 (16y ago)
Submissions
0
  1. How to make a racist AI without really trying (blog.conceptnet.io)
    6 points 0
  2. ConceptNet Numberbatch 17.04: better, less-stereotyped word vectors (blog.conceptnet.io)
    6 points 0
  3. Show HN: Announcing ConceptNet 5.5 and conceptnet.io (blog.conceptnet.io)
    5 points 0
  4. Wordfreq 1.5: More data, more languages, more accuracy (blog.conceptnet.io)
    2 points 0
  5. Yes, people do want pre-computed word embeddings (blog.conceptnet.io)
    1 points 0
  6. Cramming for the test set: We need better ways to evaluate analogies (blog.conceptnet.io)
    3 points 0
  7. Conceptnet Numberbatch: A new name for the best word embeddings you can download (blog.conceptnet.io)
    2 points 0
  8. An Introduction to the ConceptNet Vector Ensemble (blog.luminoso.com)
    16 points 0
  9. Wordfreq: Open source and open data about word frequencies (blog.luminoso.com)
    2 points 0
  10. Ftfy (fixes text for you) 4.0: changing less and fixing more (blog.luminoso.com)
    2 points 0
  11. Natural language can be such an ass headache (blog.luminoso.com)
    1 points 0
  12. Show HN: Langcodes – A Python library for working with language codes (github.com)
    5 points 0
  13. Python-ftfy: Given Unicode text, make its representation possibly less broken (github.com)
    101 points 40
  14. U+DEADBEEF: Why you shouldn't trust arbitrary text encodings (rspeer.github.io)
    1 points 0
  15. Picking a March Madness bracket using natural-language text (blog.luminoso.com)
    1 points 0
  16. Emoji are more common than hyphens (blog.luminoso.com)
    2 points 0
  17. Ftfy 3.0 — makes Unicode text less broken (blog.luminoso.com)
    2 points 0
  18. Show HN: Fixing common Unicode mistakes with Python — after they've been made (blog.lumino.so)
    4 points 0