论文标题
通过多层次学习进行层次结构实体进行排名
Hierarchical Entity Typing via Multi-level Learning to Rank
论文作者
论文摘要
我们提出了一种用于分层实体分类的新方法，该方法在训练和预测期间都包含本体论结构。在训练中，我们的新颖的多层次学习到级别的损失将正类型与否定兄弟姐妹根据类型树进行比较。在预测期间，我们定义了一个粗到精细的解码器，该解码器限制了基于已经预测的父类型的本体级别的可行候选者。我们在多个数据集中实现了最新的，尤其是在严格的准确性方面。
We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings according to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). We achieve state-of-the-art across multiple datasets, particularly with respect to strict accuracy.
