search

castorini / pygaggle

a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini
http://pygaggle.ai/
Apache License 2.0
327 stars 96 forks source link

What dose “GAR” in "Dense Passage Retrieval (DPR) Baselines" refer to ? #223

Closed XY2323819551 closed 2 years ago

XY2323819551 commented 2 years ago

Hello，I want to know whether the “GAR” in "Dense Passage Retrieval (DPR) Baselines" is the same thing in the paper which named "Generation-Augmented Retrieval for Open-Domain Question Answering"? If it is, How dose "GAR" work in your repository? Thanks in advance.😊

MXueguang commented 2 years ago

Hi @XY2323819551, we explained in this paper https://arxiv.org/abs/2104.05740. tl;dr, we take the answer span prediction rule in the GAR work. but we didn't use any generation etc from GAR work

ronakice commented 2 years ago

Resolving, open if required