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

by   Donghan Yu, et al.

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 and achieve comparable performance with FiD with only 40


Relational Graph Representation Learning for Open-Domain Question Answering

We introduce a relational graph neural network with bi-directional atten...

Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering

A common thread of open-domain question answering (QA) models employs a ...

Complex Factoid Question Answering with a Free-Text Knowledge Graph

We introduce DELFT, a factoid question answering system which combines t...

Knowledge Graph Question Answering using Graph-Pattern Isomorphism

Knowledge Graph Question Answering (KGQA) systems are based on machine l...

Transforming Visual Scene Graphs to Image Captions

We propose to Transform Scene Graphs (TSG) into more descriptive caption...

FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering

Generative models have recently started to outperform extractive models ...

Exploiting Abstract Meaning Representation for Open-Domain Question Answering

The Open-Domain Question Answering (ODQA) task involves retrieving and s...

Please sign up or login with your details

Forgot password? Click here to reset