Timeline for How to calculate the perplexity of test data versus language models
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 25, 2016 at 20:53 | comment | added | Aaron | Reporting improvements in perplexity makes people feel better because the larger scale makes the improvement seem more dramatic. | |
| Oct 24, 2016 at 14:09 | vote | accept | basil | ||
| Oct 24, 2016 at 14:09 | comment | added | basil | Thank you. I believe my problem was that my models were rather inefficient and I thought my answers must be wrong. Turns out to not be the case. As an aside: why is perplexity given more weight over entropy in determining whether or not a model is "good"? | |
| Oct 18, 2016 at 21:53 | history | answered | Aaron | CC BY-SA 3.0 |