Modeling Fine-Grained Entity Types with Box Embeddings
Modeling Fine-Grained Entity Types with Box Embeddings
复制标题
DOI：
10.18653/v1/2021.acl-long.160
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Yasumasa Onoe;Michael Boratko;Greg Durrett
中科院分区：
文献类型：
--
作者：
Yasumasa Onoe;Michael Boratko;Greg Durrett
神经实体分型模型通常代表高维空间中的媒介，但是这些空间不适合建模这些类型的复杂相互依赖性。尺寸超矩形，即使在Ontoology中明确定义这些关系的类型的层次盒子空间；从表面文本中，该模型的类型簇可以假设盒子封装的类型表示。他们自己。我们将我们的方法与基于矢量的打字模型进行了比较）Supertype和一个亚型）和置信度（即校准），证明基于盒子的模型比基于向量的模型更好地捕获潜在类型层次结构。
Neural entity typing models typically represent fine-grained entity types as vectors in a high-dimensional space, but such spaces are not well-suited to modeling these types’ complex interdependencies. We study the ability of box embeddings, which embed concepts as d-dimensional hyperrectangles, to capture hierarchies of types even when these relationships are not defined explicitly in the ontology. Our model represents both types and entity mentions as boxes. Each mention and its context are fed into a BERT-based model to embed that mention in our box space; essentially, this model leverages typological clues present in the surface text to hypothesize a type representation for the mention. Box containment can then be used to derive both the posterior probability of a mention exhibiting a given type and the conditional probability relations between types themselves. We compare our approach with a vector-based typing model and observe state-of-the-art performance on several entity typing benchmarks. In addition to competitive typing performance, our box-based model shows better performance in prediction consistency (predicting a supertype and a subtype together) and confidence (i.e., calibration), demonstrating that the box-based model captures the latent type hierarchies better than the vector-based model does.