Update readme

README.md

@@ -6,13 +6,13 @@ Dense Passage Retrieval (`DPR`)
 
 Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih, [Dense Passage Retrieval for Open-Domain Question Answering](https://arxiv.org/abs/2004.04906), EMNLP 2020.
 
-This model is the context encoder of DPR trained on TriviaQA using the [official implementation of DPR](https://github.com/facebookresearch/DPR).
+This model is the context encoder of DPR trained solely on TriviaQA (single-trivia) using the [official implementation of DPR](https://github.com/facebookresearch/DPR).
 
-Disclaimer: This model is not from the authors of DPR. It is my own reproduction. The authors did not release the DPR weights for TriviaQA.
+Disclaimer: This model is not from the authors of DPR, but my reproduction. The authors did not release the DPR weights trained solely on TriviaQA. I hope this model checkpoint can be helpful for those who want to use DPR trained only on TriviaQA.
 
 ## Performance
 
-The performance is answer recall rate measured using PyTorch 1.4.0 and transformers 4.5.0.
+The following is the answer recall rate measured using PyTorch 1.4.0 and transformers 4.5.0.
 
 The values in parentheses are those reported in the paper.
 
@@ -38,4 +38,4 @@ ctx_encoder = DPRContextEncoder.from_pretrained("soheeyang/dpr-ctx_encoder-singl
 
 data = tokenizer("context comes here", return_tensors="pt")
 ctx_embedding = ctx_encoder(**data).pooler_output  # embedding vector for context
-```
+```