论文标题
关系分类为双向跨度预测
Relation Classification as Two-way Span-Prediction
论文作者
论文摘要
当前的监督关系分类（RC）任务使用单个嵌入来表示一对实体之间的关系。我们认为，一种更好的方法是将RC任务视为跨度预测（SP）问题，类似于问题答案（QA）。我们提供了一个基于SPAN-PERTICTICT的RC系统，并与基于嵌入的系统相比评估了其性能。我们证明，受监督的SP目标的效果明显优于基于标准分类的目标。我们在Tacred和Semeval任务8数据集上实现最新结果。
The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as span-prediction (SP) problem, similar to Question answering (QA). We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. We demonstrate that the supervised SP objective works significantly better then the standard classification based objective. We achieve state-of-the-art results on the TACRED and SemEval task 8 datasets.
