Update README.md

README.md

@@ -50,9 +50,9 @@ print(result)  # e.g. [{'label': 'HAPPY', 'score': 0.99}]
 ### Training Data
 <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 The model was trained on a merged dataset from three Persian emotion corpora:
-- **ArmanEmo**: Over 7,000 Persian sentences labeled for 7 emotions. [Paper](https://arxiv.org/abs/2207.11808), [GitHub](https://github.com/Arman-Rayan-Sharif/arman-text-emotion)
-- **EmoPars**: 30,000 Persian tweets labeled with 6 basic emotions (Anger, Fear, Happiness, Sadness, Hatred, Wonder). [Paper](https://aclanthology.org/2021.ranlp-srw.23/), [GitHub](https://github.com/nazaninsbr/Persian-Emotion-Detection)
-- **ShortPersianEmo**: 5,472 short Persian texts labeled for 5 emotions (angry, sad, fear, happy, neutral). [GitHub](https://github.com/vkiani/ShortPersianEmo), [Paper](https://jad.shahroodut.ac.ir/article_3030_8c27fa0d8cb5bfba01e6835a469d3072.pdf)
+- **ArmanEmo**: Over 7,000 Persian sentences labeled for 7 emotions., [GitHub](https://github.com/Arman-Rayan-Sharif/arman-text-emotion)
+- **EmoPars**: 30,000 Persian tweets labeled with 6 basic emotions (Anger, Fear, Happiness, Sadness, Hatred, Wonder).[GitHub](https://github.com/nazaninsbr/Persian-Emotion-Detection)
+- **ShortPersianEmo**: 5,472 short Persian texts labeled for 5 emotions (angry, sad, fear, happy, neutral). [GitHub](https://github.com/vkiani/ShortPersianEmo)
 
 Datasets were standardized, cleaned (normalization with Parsivar, removal of URLs, mentions, emojis, etc.), deduplicated, and split into 90% train / 10% validation, with ArmanEmo held out for testing.
 ### Training Procedure