Update README.md

README.md

@@ -14,6 +14,8 @@ widget:
 ## MODEL DESCRIPTION
 
 huBERT base model (cased) fine-tuned on SQuAD v2 (NEW!!)
+
+"SQuAD2.0 combines the 100,000 questions in SQuAD1.1 with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. To do well on SQuAD2.0, systems must not only answer questions when possible, but also determine when no answer is supported by the paragraph and abstain from answering." [1]
 - huBert model + Tokenizer: https://huggingface.co/SZTAKI-HLT/hubert-base-cc
 - Hungarian SQUAD v2 dataset: Machine Translated SQuAD dataset (Google Translate API)
 
@@ -36,3 +38,4 @@ print(predictions)
 # output:
 # {'score': 0.9892364144325256, 'start': 16, 'end': 26, 'answer': 'Budapesten'}
 ```
+[1] https://rajpurkar.github.io/SQuAD-explorer/