Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Abstract

Commonsense question answering (QA) requires background knowledge which is not explicitly stated in a given context. Prior works use commonsense knowledge graphs (KGs) to obtain this knowledge for reasoning. However, relying entirely on these KGs may not suffice, considering their limited coverage and the contextual dependence of their knowledge. In this paper, we augment a general commonsense QA framework with a knowledgeable path generator. By extrapolating over existing paths in a KG with a state-of-the-art language model, our generator learns to connect a pair of entities in text with a dynamic, and potentially novel, multi-hop relational path. Such paths can provide structured evidence for solving commonsense questions without fine-tuning the path generator. Experiments on two datasets show the superiority of our method over previous works which fully rely on knowledge from KGs (with up to 6% improvement in accuracy), across various amounts of training data. Further evaluation suggests that the generated paths are typically interpretable, novel, and relevant to the task.

12 pages, 4 figures. Accepted to EMNLP'20 Findings

References in corpus (17)

• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
• CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches
• Abductive Commonsense Reasoning
• Probing Neural Network Comprehension of Natural Language Arguments
• How Additional Knowledge can Improve Natural Language Commonsense Question Answering?
• Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
• From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project
• Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
• Commonsense for Generative Multi-Hop Question Answering Tasks
• Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning
• Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
• Path-Based Contextualization of Knowledge Graphs for Textual Entailment
• Collaborative Policy Learning for Open Knowledge Graph Reasoning

Cited by in corpus (5)

• QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
• GNN is a Counter? Revisiting GNN for Question Answering
• Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection
• Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources
• SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning