Judge if a text answers a question (y/n)
Browse filesTake a BERT (Albert) model trained on SQUAD v2 and do transfer-learning to judge if a paragraph of Google Natural Questions Dataset answers the question.
README.md
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- tom-010/google_natural_questions_answerability
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
base_model:
|
9 |
+
- deepset/roberta-base-squad2
|
10 |
+
pipeline_tag: text-classification
|
11 |
+
---
|