RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
This work addresses the need for better information retrieval systems by proposing a joint training method, though it is incremental as it builds on existing retrieval and re-ranking techniques.
The paper tackles the problem of jointly optimizing dense passage retrieval and passage re-ranking to improve performance in natural language processing tasks, achieving effective results on MSMARCO and Natural Questions datasets.
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 re-ranking. 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/PaddlePaddle/RocketQA.