Variational Reasoning for Question Answering with Knowledge Graph

TL;DR

This paper introduces a deep learning model with variational reasoning for question answering over knowledge graphs, effectively handling noisy questions and multi-hop reasoning, achieving state-of-the-art results.

Contribution

The paper presents a novel end-to-end variational learning framework that addresses noise and multi-hop reasoning in knowledge graph question answering.

Findings

Achieved state-of-the-art performance on benchmark datasets.

Effectively handles noisy, paraphrased, and spoken questions.

Demonstrated promising results across multiple challenging datasets.

Abstract

Knowledge graph (KG) is known to be helpful for the task of question answering (QA), since it provides well-structured relational information between entities, and allows one to further infer indirect facts. However, it is challenging to build QA systems which can learn to reason over knowledge graphs based on question-answer pairs alone. First, when people ask questions, their expressions are noisy (for example, typos in texts, or variations in pronunciations), which is non-trivial for the QA system to match those mentioned entities to the knowledge graph. Second, many questions require multi-hop logic reasoning over the knowledge graph to retrieve the answers. To address these challenges, we propose a novel and unified deep learning architecture, and an end-to-end variational learning algorithm which can handle noise in questions, and learn multi-hop reasoning simultaneously. Our method achieves state-of-the-art performance on a recent benchmark dataset in the literature. We also derive a series of new benchmark datasets, including questions for multi-hop reasoning, questions paraphrased by neural translation model, and questions in human voice. Our method yields very promising results on all these challenging datasets.