%0 Conference Proceedings %T KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering %A Yu, Donghan %A Zhu, Chenguang %A Fang, Yuwei %A Yu, Wenhao %A Wang, Shuohang %A Xu, Yichong %A Ren, Xiang %A Yang, Yiming %A Zeng, Michael %Y Muresan, Smaranda %Y Nakov, Preslav %Y Villavicencio, Aline %S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) %D 2022 %8 May %I Association for Computational Linguistics %C Dublin, Ireland %F yu-etal-2022-kg %X Current Open-Domain Question Answering (ODQA) models typically include a retrieving module and a reading module, where the retriever selects potentially relevant passages from open-source documents for a given question, and the reader produces an answer based on the retrieved passages. The recently proposed Fusion-in-Decoder (FiD) framework is a representative example, which is built on top of a dense passage retriever and a generative reader, achieving the state-of-the-art performance. In this paper we further improve the FiD approach by introducing a knowledge-enhanced version, namely KG-FiD. Our new model uses a knowledge graph to establish the structural relationship among the retrieved passages, and a graph neural network (GNN) to re-rank the passages and select only a top few for further processing. Our experiments on common ODQA benchmark datasets (Natural Questions and TriviaQA) demonstrate that KG-FiD can achieve comparable or better performance in answer prediction than FiD, with less than 40% of the computation cost. %R 10.18653/v1/2022.acl-long.340 %U https://aclanthology.org/2022.acl-long.340 %U https://doi.org/10.18653/v1/2022.acl-long.340 %P 4961-4974