Generation-Augmented Retrieval for Open-domain Question Answering

Abstract

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.

Minor format updates

References in corpus (8)

• Language Models are Few-Shot Learners
• REALM: Retrieval-Augmented Language Model Pre-Training
• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
• Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation
• Overview of the TREC 2022 deep learning track
• Deep Reinforced Query Reformulation for Information Retrieval
• Few-Shot Generative Conversational Query Rewriting

Cited by in corpus (10)

• Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
• Semantic Models for the First-stage Retrieval: A Comprehensive Review
• RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
• NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
• A Replication Study of Dense Passage Retriever
• LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval
• RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
• Recent Advances in Automated Question Answering In Biomedical Domain
• Dense Hierarchical Retrieval for Open-Domain Question Answering
• What's in a Name? Answer Equivalence For Open-Domain Question Answering