soheeyang commited on
Commit
0bb7797
1 Parent(s): dda81c7

Update readme

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -4,7 +4,7 @@ Reader-Distilled Retriever (`RDR`)
4
 
5
  Sohee Yang and Minjoon Seo, [Is Retriever Merely an Approximator of Reader?](https://arxiv.org/abs/2010.10999), arXiv 2020
6
 
7
- The paper proposes to distill the reader into the retriever so that the retriever absorbs the strength of the reader while keeping its own benefit. The model is a DPR retriever further finetuned using knowledge distillation from the DPR reader. Using this approach, the answer recall rate increases by a large margin, especially at a small number of top-k.
8
 
9
  This model is the context encoder of RDR trained solely on TriviaQA (single-trivia). This model is trained by the authors and is the official checkpoint of RDR.
10
 
 
4
 
5
  Sohee Yang and Minjoon Seo, [Is Retriever Merely an Approximator of Reader?](https://arxiv.org/abs/2010.10999), arXiv 2020
6
 
7
+ The paper proposes to distill the reader into the retriever so that the retriever absorbs the strength of the reader while keeping its own benefit. The model is a DPR retriever further finetuned using knowledge distillation from the DPR reader. Using this approach, the answer recall rate increases by a large margin, especially at small numbers of top-k.
8
 
9
  This model is the context encoder of RDR trained solely on TriviaQA (single-trivia). This model is trained by the authors and is the official checkpoint of RDR.
10