Update README.md
Browse files
README.md
CHANGED
|
@@ -49,10 +49,22 @@ print(predicted_labels)
|
|
| 49 |
|
| 50 |
The INDUS-SDE-GKR model outperformed all other configurations, including the previous best alpha-1.2.1. By leveraging domain-specific pre-training on the SDE dataset and a larger context window (1024 tokens), INDUS-SDE achieved a Mean Reciprocal Rank (MRR) of 0.791, compared to 0.782 for alpha-1.2.1 and 0.744 for the ModernBERT-SDE baseline.
|
| 51 |
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
Please find accompanying [technical writeup here](https://github.com/NASA-IMPACT/science-keywords-classification/blob/develop/documents/Science_Keyword_Classification.pdf).
|
| 57 |
## References
|
| 58 |
|
|
|
|
| 49 |
|
| 50 |
The INDUS-SDE-GKR model outperformed all other configurations, including the previous best alpha-1.2.1. By leveraging domain-specific pre-training on the SDE dataset and a larger context window (1024 tokens), INDUS-SDE achieved a Mean Reciprocal Rank (MRR) of 0.791, compared to 0.782 for alpha-1.2.1 and 0.744 for the ModernBERT-SDE baseline.
|
| 51 |
|
| 52 |
+
<!-- 
|
| 53 |
+
|
| 54 |
+
 -->
|
| 55 |
+
|
| 56 |
+
<div style="display: flex; justify-content: center; align-items: center; flex-wrap: wrap;">
|
| 57 |
+
<img
|
| 58 |
+
src="https://cdn-uploads.huggingface.co/production/uploads/63f0e7de9cf89c9ed1bf92a2/CvhGPUzA2vJua3uu9H3tA.png"
|
| 59 |
+
alt="Weighted Metrics Comparison"
|
| 60 |
+
style="width: 49%; margin: 5px;"
|
| 61 |
+
>
|
| 62 |
+
<img
|
| 63 |
+
src="https://cdn-uploads.huggingface.co/production/uploads/63f0e7de9cf89c9ed1bf92a2/1mZcxlKdTh0SewEDBWpFx.png"
|
| 64 |
+
alt="INDUS-SDE GKR MRR Comparison"
|
| 65 |
+
style="width: 49%; margin: 5px;"
|
| 66 |
+
>
|
| 67 |
+
</div>
|
| 68 |
Please find accompanying [technical writeup here](https://github.com/NASA-IMPACT/science-keywords-classification/blob/develop/documents/Science_Keyword_Classification.pdf).
|
| 69 |
## References
|
| 70 |
|