期刊
APPLIED SCIENCES-BASEL
卷 11, 期 20, 页码 -出版社
MDPI
DOI: 10.3390/app11209423
关键词
semantic parsing; semantic role labeling; FrameNet; WordNet; upper ontology
This paper introduces a new method for semantic parsing with upper ontologies using FrameNet annotations and BERT-based sentence context distributed representations, designed for long text parsing. A manually annotated corpus is created as a benchmark for future studies in semantic parsing.
This paper presents a new method for semantic parsing with upper ontologies using FrameNet annotations and BERT-based sentence context distributed representations. The proposed method leverages WordNet upper ontology mapping and PropBank-style semantic role labeling and it is designed for long text parsing. Given a PropBank, FrameNet and WordNet-labeled corpus, a model is proposed that annotates the set of semantic roles with upper ontology concept names. These annotations are used for the identification of predicates and arguments that are relevant for virtual reality simulators in a 3D world with a built-in physics engine. It is shown that state-of-the-art results can be achieved in relation to semantic role labeling with upper ontology concepts. Additionally, a manually annotated corpus was created using this new method and is presented in this study. It is suggested as a benchmark for future studies relevant to semantic parsing.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据