Generation-Augmented Retrieval for Open-Domain Question Answering
Generation-Augmented Retrieval for Open-Domain Question Answering
复制标题
DOI：
10.18653/v1/2021.acl-long.316
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Yuning Mao;Pengcheng He;Xiaodong Liu;Yelong Shen;Jianfeng Gao;Jiawei Han;Weizhu Chen
中科院分区：
文献类型：
--
作者：
Yuning Mao;Pengcheng He;Xiaodong Liu;Yelong Shen;Jianfeng Gao;Jiawei Han;Weizhu Chen
我们提出了用于回答开放域问题的生成增强检索（GAR），它通过启发式发现的相关上下文的文本生成来增强查询，而不需要外部资源作为监督。我们证明了生成的上下文实质上丰富了查询的语义，并且具有稀疏表示（BM25）的GAR实现了与最先进的密集检索方法（如DPR）相当或更好的性能。我们表明，为查询生成不同的上下文是有益的，因为一致地融合它们的结果会产生更好的检索准确性。此外，由于稀疏表示和密集表示通常是互补的，GAR可以很容易地与DPR结合使用，以获得更好的性能。当配备了提取阅读器时，GAR在提取QA设置下的自然问题和TriviaQA数据集上实现了最先进的性能，并且在使用相同的生成阅读器时始终优于其他检索方法。
We propose Generation-Augmented Retrieval (GAR) for answering open-domain questions, which augments a query through text generation of heuristically discovered relevant contexts without external resources as supervision. We demonstrate that the generated contexts substantially enrich the semantics of the queries and GAR with sparse representations (BM25) achieves comparable or better performance than state-of-the-art dense retrieval methods such as DPR. We show that generating diverse contexts for a query is beneficial as fusing their results consistently yields better retrieval accuracy. Moreover, as sparse and dense representations are often complementary, GAR can be easily combined with DPR to achieve even better performance. GAR achieves state-of-the-art performance on Natural Questions and TriviaQA datasets under the extractive QA setup when equipped with an extractive reader, and consistently outperforms other retrieval methods when the same generative reader is used.