| 1. | | How to make a racist AI without really trying (conceptnet.io) |
| 6 points by rspeer on July 13, 2017 | past |
|
| 2. | | ConceptNet Numberbatch 17.04: better, less-stereotyped word vectors (conceptnet.io) |
| 6 points by rspeer on April 24, 2017 | past |
|
| 3. | | How Luminoso made ConceptNet into the best word vectors, and won at SemEval (conceptnet.io) |
| 3 points by rspeer on March 3, 2017 | past |
|
| 4. | | Show HN: Announcing ConceptNet 5.5 and conceptnet.io (conceptnet.io) |
| 5 points by rspeer on Nov 4, 2016 | past |
|
| 5. | | Wordfreq 1.5: More data, more languages, more accuracy (conceptnet.io) |
| 2 points by rspeer on Aug 22, 2016 | past |
|
| 6. | | Yes, people do want pre-computed word embeddings (conceptnet.io) |
| 1 point by rspeer on Aug 19, 2016 | past |
|
| 7. | | Cramming for the test set: We need better ways to evaluate analogies (conceptnet.io) |
| 3 points by rspeer on June 1, 2016 | past |
|
| 8. | | Conceptnet Numberbatch: A new name for the best word embeddings you can download (conceptnet.io) |
| 2 points by rspeer on May 26, 2016 | past |
|
| 9. | | An Introduction to the ConceptNet Vector Ensemble (luminoso.com) |
| 16 points by rspeer on April 7, 2016 | past |
|
| 10. | | Wordfreq: Open source and open data about word frequencies (luminoso.com) |
| 2 points by rspeer on Sept 1, 2015 | past |
|
| 11. | | Ftfy (fixes text for you) 4.0: changing less and fixing more (luminoso.com) |
| 2 points by rspeer on May 21, 2015 | past |
|
| 12. | | Natural language can be such an ass headache (luminoso.com) |
| 1 point by rspeer on Feb 17, 2015 | past |
|
| 13. | | Show HN: Langcodes – A Python library for working with language codes (github.com/luminosoinsight) |
| 5 points by rspeer on Oct 7, 2014 | past |
|
| 14. | | Python-ftfy: Given Unicode text, make its representation possibly less broken (github.com/luminosoinsight) |
| 101 points by rspeer on Aug 16, 2014 | past | 40 comments |
|
| 15. | | U+DEADBEEF: Why you shouldn't trust arbitrary text encodings (rspeer.github.io) |
| 1 point by rspeer on March 30, 2014 | past |
|
| 16. | | Picking a March Madness bracket using natural-language text (luminoso.com) |
| 1 point by rspeer on March 20, 2014 | past |
|
| 17. | | Emoji are more common than hyphens (luminoso.com) |
| 2 points by rspeer on Sept 4, 2013 | past |
|
| 18. | | Ftfy 3.0 — makes Unicode text less broken (luminoso.com) |
| 2 points by rspeer on Aug 26, 2013 | past |
|
| 19. | | Show HN: Fixing common Unicode mistakes with Python — after they've been made (lumino.so) |
| 4 points by rspeer on Aug 20, 2012 | past |
|
