Fact-Tree Reasoning for N-ary Question Answering over Knowledge Graphs

TL;DR

This paper introduces a fact-tree reasoning framework for n-ary question answering over knowledge graphs, enabling more accurate multi-hop reasoning for complex questions by transforming questions into fact trees.

Contribution

The paper proposes a novel fact-tree reasoning approach that upgrades reasoning units to facts and structures to trees, improving answer accuracy for n-ary KGQA.

Findings

Achieves high answer prediction accuracy on n-ary KGQA datasets.

Demonstrates strong reasoning ability on binary KGQA datasets.

Provides a new baseline for complex reasoning over knowledge graphs.

Abstract

In the question answering(QA) task, multi-hop reasoning framework has been extensively studied in recent years to perform more efficient and interpretable answer reasoning on the Knowledge Graph(KG). However, multi-hop reasoning is inapplicable for answering n-ary fact questions due to its linear reasoning nature. We discover that there are two feasible improvements: 1) upgrade the basic reasoning unit from entity or relation to fact; and 2) upgrade the reasoning structure from chain to tree. Based on these, we propose a novel fact-tree reasoning framework, through transforming the question into a fact tree and performing iterative fact reasoning on it to predict the correct answer. Through a comprehensive evaluation on the n-ary fact KGQA dataset introduced by this work, we demonstrate that the proposed fact-tree reasoning framework has the desired advantage of high answer prediction accuracy. In addition, we also evaluate the fact-tree reasoning framework on two binary KGQA datasets and show that our approach also has a strong reasoning ability compared with several excellent baselines. This work has direct implications for exploring complex reasoning scenarios and provides a preliminary baseline approach.