update training dataset information in README.md

README.md

@@ -18,7 +18,7 @@ tags:
 This is a pre-trained BERT language model to classify NLP-related research papers according to concepts included in the [NLP taxonomy](#nlp-taxonomy). 
 It is a multi-label classifier that can predict concepts from all levels of the NLP taxonomy. 
 If the model identifies a lower-level concept, it did learn to predict both the lower-level concept and its hypernyms in the NLP taxonomy.
-The model is fine-tuned on a weakly labeled dataset of 178,521 scientific papers from the ACL Anthology and the arXiv cs.CL domain.
+The model is fine-tuned on a weakly labeled dataset of 178,521 scientific papers from the ACL Anthology, the arXiv cs.CL domain, and Scopus.
 Prior to fine-tuning, the model is initialized with weights from [allenai/specter2](https://huggingface.co/allenai/specter2).
 
 Paper: [Exploring the Landscape of Natural Language Processing Research (RANLP 2023)](tbp).