Two is Better Than One: Answering Complex Questions by Multiple Knowledge Sources with Generalized Links

TL;DR

This paper introduces a new Multi-KB-QA task that leverages full and partial links among multiple knowledge bases, along with a novel method encoding these links to improve complex question answering performance.

Contribution

It formulates the Multi-KB-QA task considering diverse link types and proposes an encoding method that enhances answer accuracy over previous fusion-based approaches.

Findings

Our method significantly outperforms traditional KB-QA systems.

The benchmark effectively evaluates multi-KB reasoning with diversified links.

Encoding all link relations improves answer correctness in complex queries.

Abstract

Incorporating multiple knowledge sources is proven to be beneficial for answering complex factoid questions. To utilize multiple knowledge bases (KB), previous works merge all KBs into a single graph via entity alignment and reduce the problem to question-answering (QA) over the fused KB. In reality, various link relations between KBs might be adopted in QA over multi-KBs. In addition to the identity between the alignable entities (i.e. full link), unalignable entities expressing the different aspects or types of an abstract concept may also be treated identical in a question (i.e. partial link). Hence, the KB fusion in prior works fails to represent all types of links, restricting their ability to comprehend multi-KBs for QA. In this work, we formulate the novel Multi-KB-QA task that leverages the full and partial links among multiple KBs to derive correct answers, a benchmark with diversified link and query types is also constructed to efficiently evaluate Multi-KB-QA performance. Finally, we propose a method for Multi-KB-QA that encodes all link relations in the KB embedding to score and rank candidate answers. Experiments show that our method markedly surpasses conventional KB-QA systems in Multi-KB-QA, justifying the necessity of devising this task.