KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

TL;DR

KG-FiD enhances open-domain question answering by integrating a knowledge graph to filter and rerank passages, reducing noise and computational cost while improving accuracy.

Contribution

This work introduces KG-FiD, a novel method that leverages a knowledge graph and graph neural networks to improve passage filtering and reranking in ODQA.

Findings

Improves answer accuracy by up to 1.5% on benchmark datasets.

Reduces computational cost to 40% of vanilla FiD.

Achieves comparable performance with state-of-the-art models.

Abstract

Current Open-Domain Question Answering (ODQA) model paradigm often contains a retrieving module and a reading module. Given an input question, the reading module predicts the answer from the relevant passages which are retrieved by the retriever. The recent proposed Fusion-in-Decoder (FiD), which is built on top of the pretrained generative model T5, achieves the state-of-the-art performance in the reading module. Although being effective, it remains constrained by inefficient attention on all retrieved passages which contain a lot of noise. In this work, we propose a novel method KG-FiD, which filters noisy passages by leveraging the structural relationship among the retrieved passages with a knowledge graph. We initiate the passage node embedding from the FiD encoder and then use graph neural network (GNN) to update the representation for reranking. To improve the efficiency, we build the GNN on top of the intermediate layer output of the FiD encoder and only pass a few top reranked passages into the higher layers of encoder and decoder for answer generation. We also apply the proposed GNN based reranking method to enhance the passage retrieval results in the retrieving module. Extensive experiments on common ODQA benchmark datasets (Natural Question and TriviaQA) demonstrate that KG-FiD can improve vanilla FiD by up to 1.5% on answer exact match score and achieve comparable performance with FiD with only 40% of computation cost.