Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ language:
|
|
| 7 |
metrics:
|
| 8 |
- perplexity
|
| 9 |
---
|
| 10 |
-
# Model Card for `
|
| 11 |
|
| 12 |
This model is a `facebook/bart-large` fine-tuned on sarcastic comments from `raquiba/Sarcasm_News_Headline` dataset.
|
| 13 |
|
|
@@ -15,7 +15,7 @@ This model is a `facebook/bart-large` fine-tuned on sarcastic comments from `raq
|
|
| 15 |
|
| 16 |
This model is not intended to be used for plain inference as it is very likely to predict sarcastic content.
|
| 17 |
It is intended to be used instead as "utility model" for detecting and fixing sarcastic content as its token probability distributions will likely differ from comparable models not trained/fine-tuned over sarcastic data.
|
| 18 |
-
Its name `
|
| 19 |
|
| 20 |
### Model Description
|
| 21 |
|
|
|
|
| 7 |
metrics:
|
| 8 |
- perplexity
|
| 9 |
---
|
| 10 |
+
# Model Card for `sarcasm_minus`
|
| 11 |
|
| 12 |
This model is a `facebook/bart-large` fine-tuned on sarcastic comments from `raquiba/Sarcasm_News_Headline` dataset.
|
| 13 |
|
|
|
|
| 15 |
|
| 16 |
This model is not intended to be used for plain inference as it is very likely to predict sarcastic content.
|
| 17 |
It is intended to be used instead as "utility model" for detecting and fixing sarcastic content as its token probability distributions will likely differ from comparable models not trained/fine-tuned over sarcastic data.
|
| 18 |
+
Its name `sarcasm_minus` refers to the _G-_ model in [Detoxifying Text with MARCO: Controllable Revision with Experts and Anti-Experts](https://aclanthology.org/2023.acl-short.21.pdf).
|
| 19 |
|
| 20 |
### Model Description
|
| 21 |
|