Commit ·
ec65d64
1
Parent(s): 8d30fea
update
Browse files
README.md
CHANGED
|
@@ -25,8 +25,8 @@ model-index:
|
|
| 25 |
|
| 26 |
# Turkish SQuAD Model : Question Answering
|
| 27 |
|
| 28 |
-
I fine-tuned Loodos-Turkish-Bert-Model for Question-Answering problem with TQuAD dataset
|
| 29 |
-
* Loodos-BERT-base: https://huggingface.co/loodos/bert-base-turkish-uncased
|
| 30 |
* TQuAD dataset: https://github.com/TQuad/turkish-nlp-qa-dataset
|
| 31 |
|
| 32 |
|
|
|
|
| 25 |
|
| 26 |
# Turkish SQuAD Model : Question Answering
|
| 27 |
|
| 28 |
+
I fine-tuned Loodos-Turkish-Bert-Model for Question-Answering problem with TQuAD dataset. Since the "loodos/bert-base-turkish-uncased" model gave the best results for the Turkish language in classification in the "Auto-tagging of Short Conversational Sentences using Transformer Methods" research we conducted with my teammates, I used this model because I thought that the success rate could be high in the question-answering.
|
| 29 |
+
* Loodos-BERT-base-uncased: https://huggingface.co/loodos/bert-base-turkish-uncased
|
| 30 |
* TQuAD dataset: https://github.com/TQuad/turkish-nlp-qa-dataset
|
| 31 |
|
| 32 |
|