Entity Retrieval for Answering Entity-Centric Questions
Abstract: The similarity between the question and indexed documents is a crucial factor in document retrieval for retrieval-augmented question answering. Although this is typically the only method for obtaining the relevant documents, it is not the sole approach when dealing with entity-centric questions. In this study, we propose Entity Retrieval, a novel retrieval method which rather than relying on question-document similarity, depends on the salient entities within the question to identify the retrieval documents. We conduct an in-depth analysis of the performance of both dense and sparse retrieval methods in comparison to Entity Retrieval. Our findings reveal that our method not only leads to more accurate answers to entity-centric questions but also operates more efficiently.
Paper Type: Long
Research Area: Question Answering
Research Area Keywords: Information Retrieval, Information Extraction, Generation, Question Answering
Contribution Types: Model analysis & interpretability, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models
Languages Studied: English
Submission Number: 2062
Loading