Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering

Citations Over Time

Abstract

In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop QA, where aggregating information from multiple pieces of information and reasoning over them is required. Despite their success, dense retrieval methods are computationally intensive, requiring multiple GPUs to train. In this work, we introduce a hybrid (lexical and dense) retrieval approach that is highly competitive with the state-of-the-art dense retrieval models, while requiring substantially less computational resources. Additionally, we provide an in-depth evaluation of dense retrieval methods on limited computational resource settings, something that is missing from the current literature.

Related Papers

• → Question Answering in the Biomedical Domain(2019)10 cited
• Advances in Open-Domain Question Answering(2009)
• → Open-Domain Conversational Question Answering with Historical Answers(2022)4 cited
• → Zero-Shot Open-Book Question Answering(2021)1 cited
• → MSReNet: Multi-step Reformulation for Open-Domain Question Answering(2020)