Update README.md
Browse files
README.md
CHANGED
|
@@ -29,7 +29,6 @@ which are annotated for factual consistency using **FLAN-PaLM 540B** [(Chung et
|
|
| 29 |
Summaries were generated using summarization models which were trained on the **XSum** dataset [(Narayan et al., 2018)](https://aclanthology.org/D18-1206.pdf).
|
| 30 |
|
| 31 |
The input format for the model is: "premise: GROUNDING_DOCUMENT hypothesis: HYPOTHESIS_SUMMARY".
|
| 32 |
-
|
| 33 |
To accomodate the input length of common summarization datasets we recommend setting **max_length** to **2048**.
|
| 34 |
|
| 35 |
The model predicts a binary label ('1' - Factualy Consistent, '0' - Factualy Inconsistent).
|
|
|
|
| 29 |
Summaries were generated using summarization models which were trained on the **XSum** dataset [(Narayan et al., 2018)](https://aclanthology.org/D18-1206.pdf).
|
| 30 |
|
| 31 |
The input format for the model is: "premise: GROUNDING_DOCUMENT hypothesis: HYPOTHESIS_SUMMARY".
|
|
|
|
| 32 |
To accomodate the input length of common summarization datasets we recommend setting **max_length** to **2048**.
|
| 33 |
|
| 34 |
The model predicts a binary label ('1' - Factualy Consistent, '0' - Factualy Inconsistent).
|