Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering
This work addresses the high computational cost of dense retrieval for multi-hop QA, making it more accessible for researchers and practitioners with limited resources.
The paper tackles the computational inefficiency of dense retrieval methods in multi-hop question answering by introducing a hybrid lexical and dense retrieval approach that achieves competitive performance with state-of-the-art models while requiring substantially less computational resources, as demonstrated through evaluations in limited-resource settings.
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.