论文标题
与类型抽象的开放关系和事件类型发现
Open Relation and Event Type Discovery with Type Abstraction
论文作者
论文摘要
常规的封闭世界信息提取（IE）方法依赖于人本体来定义提取范围。结果，当应用于新域时，这种方法缺乏。这要求系统可以自动从给定语料库中推断新类型的系统，这是我们称为类型发现的任务。为了解决这个问题，我们介绍了类型抽象的想法，该想法提示该模型概括和命名类型。然后，我们使用推断名称之间的相似性来诱导集群。观察到这种基于抽象的表示通常与实体/触发令牌表示形式互补，我们将这两个表示形式设置为两种视图，并将我们的模型设计为共同训练框架。我们对多个关系提取和事件提取数据集的实验始终显示出我们类型抽象方法的优势。可在https://github.com/raspberryice/type-discovery-abs上找到代码。
Conventional closed-world information extraction (IE) approaches rely on human ontologies to define the scope for extraction. As a result, such approaches fall short when applied to new domains. This calls for systems that can automatically infer new types from given corpora, a task which we refer to as type discovery. To tackle this problem, we introduce the idea of type abstraction, where the model is prompted to generalize and name the type. Then we use the similarity between inferred names to induce clusters. Observing that this abstraction-based representation is often complementary to the entity/trigger token representation, we set up these two representations as two views and design our model as a co-training framework. Our experiments on multiple relation extraction and event extraction datasets consistently show the advantage of our type abstraction approach. Code available at https://github.com/raspberryice/type-discovery-abs.
