Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
arxiv: 2605.11336
|
| 3 |
tags:
|
| 4 |
- setfit
|
| 5 |
- sentence-transformers
|
|
@@ -26,7 +25,7 @@ license: mit
|
|
| 26 |
|
| 27 |
A binary [SetFit](https://github.com/huggingface/setfit) classifier that distinguishes geospatial
|
| 28 |
from non-geospatial web search queries. Trained on 1,200 gold-labelled
|
| 29 |
-
[MS MARCO](https://microsoft.github.io/msmarco/) web search queries with weak supervision from Llama 3.1, then manually verified.
|
| 30 |
|
| 31 |
Achieves **F1 = 0.931** on a held-out test set of 800 samples (421 non-spatial, 379 spatial),
|
| 32 |
with the evaluation model trained on 200 samples (105 non-spatial, 95 spatial). The deployed model was trained on the full 1,200.
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
tags:
|
| 3 |
- setfit
|
| 4 |
- sentence-transformers
|
|
|
|
| 25 |
|
| 26 |
A binary [SetFit](https://github.com/huggingface/setfit) classifier that distinguishes geospatial
|
| 27 |
from non-geospatial web search queries. Trained on 1,200 gold-labelled
|
| 28 |
+
[MS MARCO](https://microsoft.github.io/msmarco/) web search queries with weak supervision from Llama 3.1, then manually verified. See COSIT 2026 paper preprint here - https://arxiv.org/abs/2605.11336
|
| 29 |
|
| 30 |
Achieves **F1 = 0.931** on a held-out test set of 800 samples (421 non-spatial, 379 spatial),
|
| 31 |
with the evaluation model trained on 200 samples (105 non-spatial, 95 spatial). The deployed model was trained on the full 1,200.
|