login
Home / Papers / Generation-Augmented Retrieval for Open-Domain Question Answering

Generation-Augmented Retrieval for Open-Domain Question Answering

135 Citations2021
Yuning Mao, Pengcheng He, Xiaodong Liu
journal unavailable

It is shown that generating diverse contexts for a query is beneficial as fusing their results consistently yields better retrieval accuracy, and as sparse and dense representations are often complementary, GAR can be easily combined with DPR to achieve even better performance.

Abstract

Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Generation-Augmented Retrieval for Open-Domain Question Answ