论文标题
DualtkB：文本和知识库之间的双重学习桥
DualTKB: A Dual Learning Bridge between Text and Knowledge Base
论文作者
论文摘要
在这项工作中，我们为无监督的文本提供了一种双重学习方法，以通往常识性知识库（KBS）中文本传输的路径和路径。我们通过创建一个弱监督的数据集来研究弱监督的影响，并表明即使少量监督也可以显着改善模型性能并实现更好的转移。我们检查了不同的模型架构和评估指标，提出了一种针对生成模型量身定制的新常识性KB完成度量。广泛的实验结果表明，该提出的方法与现有基线相比非常有利。这种方法是迈出更先进的系统的可行步骤，用于自动KB构造/扩展以及KB转换为连贯的文本描述的反向操作。
In this work, we present a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases (KBs). We investigate the impact of weak supervision by creating a weakly supervised dataset and show that even a slight amount of supervision can significantly improve the model performance and enable better-quality transfers. We examine different model architectures, and evaluation metrics, proposing a novel Commonsense KB completion metric tailored for generative models. Extensive experimental results show that the proposed method compares very favorably to the existing baselines. This approach is a viable step towards a more advanced system for automatic KB construction/expansion and the reverse operation of KB conversion to coherent textual descriptions.
