Conventional entity typing approaches are based on independent classification
paradigms, which make them difficult to recognize inter-dependent, long-tailed
and fine-grained entity types. In this paper, we argue that the implicitly
entailed extrinsic and intrinsic dependencies between labels can provide
critical knowledge to tackle the above challenges. To this end, we propose
\emph{Label Reasoning Network(LRN)}, which sequentially reasons fine-grained
entity labels by discovering and exploiting label dependencies knowledge
entailed in the data. Specifically, LRN utilizes an auto-regressive network to
conduct deductive reasoning and a bipartite attribute graph to conduct
inductive reasoning between labels, which can effectively model, learn and
reason complex label dependencies in a sequence-to-set, end-to-end manner.
Experiments show that LRN achieves the state-of-the-art performance on standard
ultra fine-grained entity typing benchmarks, and can also resolve the long tail
label problem effectively.

该论文提出了 Label Reasoning Network (LRN)，通过发现和利用数据中隐含的外在和内在依赖关系知识，从而顺序推理细粒度实体标签，有效地建模、学习和推理复杂标签依赖关系，从而解决实体类型分类的挑战。实验结果表明，LRN 在标准超细粒度实体类型分类基准上实现了最先进的性能，并且可以有效地解决长尾标签问题。