论文标题
连接点：用于常识性问题的知识渊博的路径发生器回答
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
论文作者
论文摘要
常识性问题回答（QA）需要在给定情况下没有明确说明的背景知识。先前的工作使用常识知识图（kgs）来获取这些知识以进行推理。但是，考虑到它们的知识有限和上下文依赖性，完全依靠这些KG可能不够。在本文中，我们通过知识渊博的路径生成器来增强通用常识性质量检查框架。通过使用最先进的语言模型在千克中推断现有路径，我们的发电机学会了将文本中的一对实体与动态的，潜在的新型多跳的关系路径连接起来。这样的路径可以为解决常识性问题提供结构化证据，而无需微调路径发生器。在两个数据集上的实验表明，在各种培训数据中，我们方法比以前的作品的优越性超过了以前的作品，这些工作完全依赖于KGS的知识（准确性提高了6％）。进一步的评估表明，生成的路径通常可以解释，新颖，并且与任务相关。
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.
