论文标题
可通用的通用神经符号系统回答
Generalizable Neuro-symbolic Systems for Commonsense Question Answering
论文作者
论文摘要
本章说明了用于语言理解的合适神经符号模型如何在下游任务中启用域的普遍性和鲁棒性。讨论了整合神经语言模型和知识图的不同方法。该组合最合适的情况是特征的，包括对各种常识性问题回答基准数据集的定量评估和定性错误分析。
This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are discussed. The situations in which this combination is most appropriate are characterized, including quantitative evaluation and qualitative error analysis on a variety of commonsense question answering benchmark datasets.
