Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals

Abstract

Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only receive the feedback from the final answer, which makes the learning unstable or ineffective. To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network. The major novelty lies in the design of the teacher network, where we utilize both forward and backward reasoning to enhance the learning of intermediate entity distributions. By considering bidirectional reasoning, the teacher network can produce more reliable intermediate supervision signals, which can alleviate the issue of spurious reasoning. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our approach on the KBQA task. The code to reproduce our analysis is available at https://github.com/RichardHGL/WSDM2021_NSM.

WSDM 2021 camer-ready version. 9 pages, code on https://github.com/RichardHGL/WSDM2021_NSM

References in corpus (10)

• Distilling the Knowledge in a Neural Network
• Semi-Supervised Classification with Graph Convolutional Networks
• FitNets: Hints for Thin Deep Nets
• Born Again Neural Networks
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• Variational Reasoning for Question Answering with Knowledge Graph
• Compositional Attention Networks for Machine Reasoning
• Language-Conditioned Graph Networks for Relational Reasoning
• Learning by Abstraction: The Neural State Machine
• Compact Trilinear Interaction for Visual Question Answering

Cited by in corpus (7)

• Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
• Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning
• KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
• A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
• LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration
• Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph
• Beyond NED: Fast and Effective Search Space Reduction for Complex Question Answering over Knowledge Bases