Entity Retrieval for Answering Entity-Centric Questions
Hassan S. Shavarani, Anoop Sarkar

TL;DR
This paper introduces Entity Retrieval, a new method for fetching documents based on key entities in questions, improving accuracy and efficiency for entity-centric question answering.
Contribution
The paper presents Entity Retrieval, a novel approach that shifts from similarity-based retrieval to entity-based retrieval for better entity-centric question answering.
Findings
Entity Retrieval improves answer accuracy for entity-centric questions.
The method operates more efficiently than traditional similarity-based retrieval.
Both dense and sparse retrieval methods are analyzed in comparison.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Service-Oriented Architecture and Web Services · Web Data Mining and Analysis
