Commit ·
15d3a06
1
Parent(s): 7927134
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,15 +4,15 @@ license: apache-2.0
|
|
| 4 |
|
| 5 |
## Model description
|
| 6 |
|
| 7 |
-
|
| 8 |
|
| 9 |
-
The question type classifier takes as input the question, and returns a label that distinguishes boolean and extractive questions.
|
| 10 |
|
| 11 |
The model was initialized with [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) and fine-tuned on the answerable subset of [TyDiQA](https://huggingface.co/datasets/tydiqa) train questions.
|
| 12 |
|
| 13 |
## Intended uses & limitations
|
| 14 |
|
| 15 |
-
You can use the raw model for question classification. Biases associated with the pre-existing language model, bert-base-multilingual-cased,
|
| 16 |
|
| 17 |
## Usage
|
| 18 |
|
|
|
|
| 4 |
|
| 5 |
## Model description
|
| 6 |
|
| 7 |
+
A question type classification model based on multilingual BERT.
|
| 8 |
|
| 9 |
+
The question type classifier takes as input the question, and returns a label that distinguishes between boolean and short answer extractive questions.
|
| 10 |
|
| 11 |
The model was initialized with [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) and fine-tuned on the answerable subset of [TyDiQA](https://huggingface.co/datasets/tydiqa) train questions.
|
| 12 |
|
| 13 |
## Intended uses & limitations
|
| 14 |
|
| 15 |
+
You can use the raw model for question classification. Biases associated with the pre-existing language model, bert-base-multilingual-cased, may be present in our fine-tuned model, tydiqa-boolean-question-classifier.
|
| 16 |
|
| 17 |
## Usage
|
| 18 |
|