Knowledge Commons of Institute of Automation,CAS
Prediction and Calibration: Complex Reasoning over Knowledge Graph with Bi-directional Directed Acyclic Graph Neural Network | |
Yao Xu1,2![]() ![]() ![]() | |
2023-07-09 | |
会议名称 | The 61st Annual Meeting of the Association for Computational Linguistics |
会议日期 | 2023.07.09-2023.07.14 |
会议地点 | Toronto, Canada |
摘要 | Answering complex logical queries is a challenging task for knowledge graph (KG) reasoning. Recently, query embedding (QE) has been proposed to encode queries and entities into the same vector space, and obtain answers based on numerical computation. However, such models obtain the node representations of a query only based on its predecessor nodes, which ignore the information contained in successor nodes. In this paper, we proposed a Bi-directional Directed Acyclic Graph neural network (BiDAG) that splits the reasoning process into prediction and calibration. The joint probability of all nodes is considered by applying a graph neural network (GNN) to the query graph in the calibration process. By the prediction in the first layer and the calibration in deep layers of GNN, BiDAG can outperform previous QE based methods on FB15k, FB15k-237, and NELL995. |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57450 |
专题 | 复杂系统认知与决策实验室 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Meituan |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yao Xu,Shizhu HE,Li Cai,et al. Prediction and Calibration: Complex Reasoning over Knowledge Graph with Bi-directional Directed Acyclic Graph Neural Network[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Prediction and Calib(628KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Yao Xu]的文章 |
[Shizhu HE]的文章 |
[Li Cai]的文章 |
百度学术 |
百度学术中相似的文章 |
[Yao Xu]的文章 |
[Shizhu HE]的文章 |
[Li Cai]的文章 |
必应学术 |
必应学术中相似的文章 |
[Yao Xu]的文章 |
[Shizhu HE]的文章 |
[Li Cai]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论