Commit
·
5149d19
1
Parent(s):
da56149
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,37 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language: tr
|
| 3 |
+
tags:
|
| 4 |
+
- roberta
|
| 5 |
+
- language-model
|
| 6 |
+
- scientific
|
| 7 |
+
- turkish
|
| 8 |
license: mit
|
| 9 |
+
model_author: Serdar ÇAĞLAR
|
| 10 |
---
|
| 11 |
+
|
| 12 |
+
# Roberta-Based Language Model Trained on Turkish Scientific Article Abstracts
|
| 13 |
+
|
| 14 |
+
This model is a powerful natural language processing model trained on Turkish scientific article summaries. It focuses on scientific content in the Turkish language and excels in tasks related to text comprehension. The model can be used for understanding scientific texts, summarization, and various other natural language processing tasks.
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
- **Data Source**: This model is trained on a custom dataset consisting of Turkish scientific article summaries. The data was collected using web scraping methods from various sources in Turkey, including databases like "trdizin," "yöktez," and "türkiyeklinikler."
|
| 19 |
+
|
| 20 |
+
- **Dataset Preprocessing**: The data underwent preprocessing to facilitate better learning. Texts were segmented into sentences, and improperly divided sentences were cleaned. The texts were processed meticulously.
|
| 21 |
+
|
| 22 |
+
- **Tokenizer**: The model utilizes a BPE (Byte Pair Encoding) tokenizer to process the data effectively, breaking down the text into subword tokens.
|
| 23 |
+
|
| 24 |
+
- **Training Details**: The model was trained on a large dataset of Turkish sentences. Training spanned 10 epochs, totaling 240 hours, and the model was built from scratch. No fine-tuning was applied.
|
| 25 |
+
|
| 26 |
+
## Usage
|
| 27 |
+
|
| 28 |
+
This model is compatible with Hugging Face's Transformers library and can be employed in various natural language processing projects and applications.
|
| 29 |
+
|
| 30 |
+
## Disclaimer
|
| 31 |
+
|
| 32 |
+
The use of this model is subject to compliance with specific copyright and legal regulations, which are the responsibility of the users. The model owner or provider cannot be held liable for any issues arising from the use of the model.
|
| 33 |
+
|
| 34 |
+
## Model Owner
|
| 35 |
+
|
| 36 |
+
This model was developed by Serdar ÇAĞLAR. For more information about the developer, you can visit [his LinkedIn profile](https://www.linkedin.com/in/serdarildercaglar/).
|
| 37 |
+
|