Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering

Abstract

Existing work on augmenting question answering (QA) models with external knowledge (e.g., knowledge graphs) either struggle to model multi-hop relations efficiently, or lack transparency into the model's prediction rationale. In this paper, we propose a novel knowledge-aware approach that equips pre-trained language models (PTLMs) with a multi-hop relational reasoning module, named multi-hop graph relation network (MHGRN). It performs multi-hop, multi-relational reasoning over subgraphs extracted from external knowledge graphs. The proposed reasoning module unifies path-based reasoning methods and graph neural networks to achieve better interpretability and scalability. We also empirically show its effectiveness and scalability on CommonsenseQA and OpenbookQA datasets, and interpret its behaviors with case studies.

Accepted to EMNLP 2020. Project page: https://github.com/INK-USC/MHGRN

References in corpus (7)

• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
• FreeLB: Enhanced Adversarial Training for Natural Language Understanding
• Align, Mask and Select: A Simple Method for Incorporating Commonsense Knowledge into Language Representation Models
• Dynamic Integration of Background Knowledge in Neural NLU Systems
• KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
• Teaching Pretrained Models with Commonsense Reasoning: A Preliminary KB-Based Approach

Cited by in corpus (8)

• Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution
• GNN is a Counter? Revisiting GNN for Question Answering
• Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
• Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
• Fusing Context Into Knowledge Graph for Commonsense Question Answering
• Enriching Ontology with Temporal Commonsense for Low-Resource Audio Tagging
• SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning
• A Universal Model for Cross Modality Mapping by Relational Reasoning