Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
This addresses the challenge of providing structured, interpretable evidence for commonsense question answering, offering a novel hybrid approach that enhances reasoning without fine-tuning, though it is incremental in combining existing techniques.
The paper tackles the problem of limited coverage and contextual dependence in commonsense knowledge graphs for question answering by augmenting a QA framework with a knowledgeable path generator that extrapolates over existing paths using a language model to create dynamic, multi-hop relational paths. The result is up to 6% improvement in accuracy on two datasets compared to methods relying solely on knowledge graphs.
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.