报告题目：RocketQAv2 A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking

论文出处：《EMNLP》

作者：Ruiyang Ren, Yingqi Qu2, Jing Liu, Kai Liu, Wayne Xin Zhao, Qiaoqiao She, Hua Wu, Haifeng Wang, and Ji-Rong Wen

单位：School of Information, Renmin University of China；Baidu Inc；Beijing Key Laboratory of Big Data Management and Analysis Methods；Gaoling School of Artificial Intelligence, Renmin University of China

报告人：李佳丽

报告时间：2022年10月17日 

报告地点：贵州大学北校区博学楼624室

报告内容摘要：In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to jointly optimize them in order to achieve mutual improvement. In this paper, we propose a novel joint training approach for dense passage retrieval and passage reranking. A major contribution is that we introduce the dynamic listwise distillation, where we design a unified listwise training approach for both the retriever and the re-ranker. During the dynamic distillation, the retriever and the re-ranker can be adaptively improved according to each other’s relevance information. We also propose a hybrid data augmentation strategy to construct diverse training instances for listwise training approach. Extensive experiments show the effectiveness of our approach on both MSMARCO and Natural Questions datasets. Our code is available at https://github.com/PaddlePadle/RocketQA.