Generation-Augmented Retrieval for Open-domain Question Answering

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.

PDF Abstract ACL 2021 PDF ACL 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Passage Retrieval Natural Questions BM25+RM3 Precision@20 64.2 # 7
Precision@100 79.6 # 8


No methods listed for this paper. Add relevant methods here