Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,12 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- google/canine-s
|
| 5 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- google/canine-s
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
This is an artifact of the SNAILS project. We finetuned google/canine-s to perform the task of word naturalness classification.
|
| 8 |
+
Full (unabbreviated) words are "Regular" naturalness (labeled as N1). Somewhat abbreviated words are "Low" naturalness (labeled as N2).
|
| 9 |
+
Very abbreviated or indecipherable words are "Least" naturalness (labeled as N3).
|
| 10 |
+
|
| 11 |
+
Inference using this model requires a token tagging pre-processing step. This is provided in tokenprocessing.py.
|
| 12 |
+
To most easily use this model, download the canine_naturalness_classifier.py and tokenprocessing.py files in this
|
| 13 |
+
repository and run.
|