论文标题
框架语义解析的基于双层的框架
A Double-Graph Based Framework for Frame Semantic Parsing
论文作者
论文摘要
框架语义解析是一项基本的NLP任务，由三个子任务组成：框架标识，参数识别和角色分类。以前的大多数研究倾向于忽略不同的子任务和论点之间的关系，而很少关注Framenet中定义的本体论框架知识。在本文中，我们提出了一个带有双层（KID）的知识引导的增量语义解析器。我们首先介绍框架知识图（FKG），这是一个构建框架知识上构建的帧和FES（帧元素）的异质图，以便我们可以为框架和FES得出知识增强的表示。此外，我们提出了框架语义图（FSG）来表示用图形结构从文本中提取的框架语义结构。这样，我们可以将框架语义解析转换为增量图构造问题，以加强子任务与参数之间的关系之间的相互作用。我们的实验表明，在两个Framenet数据集上，KID的表现优于先前的最新方法1.7 f1得分。我们的代码可在https://github.com/pkunlp-icler/kid上使用。
Frame semantic parsing is a fundamental NLP task, which consists of three subtasks: frame identification, argument identification and role classification. Most previous studies tend to neglect relations between different subtasks and arguments and pay little attention to ontological frame knowledge defined in FrameNet. In this paper, we propose a Knowledge-guided Incremental semantic parser with Double-graph (KID). We first introduce Frame Knowledge Graph (FKG), a heterogeneous graph containing both frames and FEs (Frame Elements) built on the frame knowledge so that we can derive knowledge-enhanced representations for frames and FEs. Besides, we propose Frame Semantic Graph (FSG) to represent frame semantic structures extracted from the text with graph structures. In this way, we can transform frame semantic parsing into an incremental graph construction problem to strengthen interactions between subtasks and relations between arguments. Our experiments show that KID outperforms the previous state-of-the-art method by up to 1.7 F1-score on two FrameNet datasets. Our code is availavle at https://github.com/PKUnlp-icler/KID.
