Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Alec
commited on
Commit
•
50099fe
1
Parent(s):
f5b5065
update image size
Browse files
README.md
CHANGED
|
@@ -43,11 +43,11 @@ We've provided a starter baseline which trains a logistic regression detector on
|
|
| 43 |
|
| 44 |
### Initial Analysis
|
| 45 |
|
| 46 |
-
|
| 47 |
|
| 48 |
Shorter documents are harder to detect. Accuracy of detection of a short documents of 500 characters (a long paragraph) is about 15% lower.
|
| 49 |
|
| 50 |
-
|
| 51 |
|
| 52 |
Truncated sampling, which is commonly used for high-quality generations from the GPT-2 model family, results in a shift in the part of speech distribution of the generated text compared to real text. A clear example is the underuse of proper nouns and overuse of pronouns which are more generic. This shift contributes to the 8% to 18% higher detection rate of Top-K samples compared to random samples across models.
|
| 53 |
|
|
|
|
| 43 |
|
| 44 |
### Initial Analysis
|
| 45 |
|
| 46 |
+
<img src="https://i.imgur.com/PZ3GOeS.png" width="723.0" height="450" title="Impact of Document Length">
|
| 47 |
|
| 48 |
Shorter documents are harder to detect. Accuracy of detection of a short documents of 500 characters (a long paragraph) is about 15% lower.
|
| 49 |
|
| 50 |
+
<img src="https://i.imgur.com/eH9Ogqo.png" width="713.0" height="502" title="Part of Speech Analysis">
|
| 51 |
|
| 52 |
Truncated sampling, which is commonly used for high-quality generations from the GPT-2 model family, results in a shift in the part of speech distribution of the generated text compared to real text. A clear example is the underuse of proper nouns and overuse of pronouns which are more generic. This shift contributes to the 8% to 18% higher detection rate of Top-K samples compared to random samples across models.
|
| 53 |
|