论文标题
富含类型的层次对比策略
Type-enriched Hierarchical Contrastive Strategy for Fine-Grained Entity Typing
论文作者
论文摘要
细粒度实体打字（FET）旨在推断实体中提到的特定语义类型。 FET的现代方法主要集中于学习某种类型的外观。很少有作品直接建模类型差异，即，让模型知道一种类型与其他类型不同的程度。为了减轻这个问题，我们提出了一种富含类型的FET的分层对比策略。我们的方法可以直接建模分层类型之间的差异，并提高区分多元类似类型的能力。一方面，我们将类型嵌入实体上下文中，以使类型信息直接可感知。另一方面，我们在层次结构上设计了一个约束的对比策略，以直接建模类型差异，这可以同时感知不同粒度下类型之间的区分性。 BBN，Ontonotes和Figer的三个基准测试结果的实验结果表明，我们的方法通过有效建模类型差异在FET上实现了显着性能。
Fine-grained entity typing (FET) aims to deduce specific semantic types of the entity mentions in text. Modern methods for FET mainly focus on learning what a certain type looks like. And few works directly model the type differences, that is, let models know the extent that one type is different from others. To alleviate this problem, we propose a type-enriched hierarchical contrastive strategy for FET. Our method can directly model the differences between hierarchical types and improve the ability to distinguish multi-grained similar types. On the one hand, we embed type into entity contexts to make type information directly perceptible. On the other hand, we design a constrained contrastive strategy on the hierarchical structure to directly model the type differences, which can simultaneously perceive the distinguishability between types at different granularity. Experimental results on three benchmarks, BBN, OntoNotes, and FIGER show that our method achieves significant performance on FET by effectively modeling type differences.
