论文标题
猎犬只是读者的近似值吗？
Is Retriever Merely an Approximator of Reader?
论文作者
论文摘要
开放域问题回答（QA）中的最新技术取决于有效的检索器，该检索器大大降低了昂贵的读者的搜索空间。社区中一个相当忽视的问题是猎犬和读者之间的关系，尤其是，如果猎犬的全部目的只是读者的快速近似值。我们的经验证据表明，答案是否定的，即使仅在准确性方面，读者和检修器也相互互补。我们谨慎地猜想，最初打算用于实现近似搜索的猎犬的建筑约束似乎也使模型在大规模搜索中更加可靠。然后，我们建议将读者提取到猎犬中，以便猎犬在保持自己的利益的同时吸收读者的力量。实验结果表明，我们的方法可以提高文档召回率以及在开放域QA任务中现成的检索器的端到端质量检查精度。
The state of the art in open-domain question answering (QA) relies on an efficient retriever that drastically reduces the search space for the expensive reader. A rather overlooked question in the community is the relationship between the retriever and the reader, and in particular, if the whole purpose of the retriever is just a fast approximation for the reader. Our empirical evidence indicates that the answer is no, and that the reader and the retriever are complementary to each other even in terms of accuracy only. We make a careful conjecture that the architectural constraint of the retriever, which has been originally intended for enabling approximate search, seems to also make the model more robust in large-scale search. We then propose to distill the reader into the retriever so that the retriever absorbs the strength of the reader while keeping its own benefit. Experimental results show that our method can enhance the document recall rate as well as the end-to-end QA accuracy of off-the-shelf retrievers in open-domain QA tasks.
