用于常识本体预测的改进表示学习
Improved Representation Learning for Predicting Commonsense Ontologies
摘要：
最近在学习本体（分层和部分有序结构）的工作已经利用了学习表示空间的内在几何结构来进行自动遵守复杂结构约束的预测。我们探讨了这样一个模型的两个扩展，层次关系学习的顺序嵌入模型，目的是提高性能的常识知识表示的文本数据。我们的第一个模型以原始文本的形式联合学习排序关系和非层次知识。我们的第二个扩展利用偏序结构的训练数据，找到长距离的三重约束之间的嵌入，这是执行不良的成对训练过程。我们发现，结合自由文本和增强的训练约束都优于原始的顺序嵌入模型和其他强基线。
英文摘要：
Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints. We explore two extensions of one such model, the order-embedding model for hierarchical relation learning, with an aim towards improved performance on text data for commonsense knowledge representation. Our first model jointly learns ordering relations and non-hierarchical knowledge in the form of raw text. Our second extension exploits the partial order structure of the training data to find long-distance triplet constraints among embeddings which are poorly enforced by the pairwise training procedure. We find that both incorporating free text and augmented training constraints improve over the original order-embedding model and other strong baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
