Ken Schutte personal blog
Gzip beats BERT? Part 2: dataset issues, improved speed, and results
Summary : Update to my last post analyzing the gzip+knn paper. Some of the datasets have heavily contaminated train/test tests. I show some ways to significantly speed-up the gzip method. I present more results of my "fair" reimplementation .
- Points
- 248
- HN comments
- 51
- Submissions
- 1
- Cited by
- 3 commenters
AI & Machine LearningDatabases & Data2023
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jul 29, 2023 | Gzip beats BERT? Part 2: dataset issues, improved speed, and results by JoeyBananas | 248 | 51 |
Cited in comments
Linked from 4 Hacker News comments by 3 different people, from Jul 2023 to Feb 2026.
Most recent:
- ks2048 · Feb 11, 2026
- isoprophlex · Sep 24, 2023
- liliumregale · Jul 29, 2023
- liliumregale · Jul 29, 2023
