arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.05925cs.CLcs.AI
收藏

常识知识图谱的选择推理还是生成推理?为什么?为什么?

Commonsense Knowledge Graph Reasoning by Selection or Generation? Why?

School of Engineering, Westlake University(西湖大学工学院);Zhejiang University(浙江大学);Alibaba Inc(阿里巴巴公司)

Cunxiang Wang, Jinhang Wu, Luxin Liu, Yue Zhang

摘要:

常识知识图谱推理(CKGR)是在已知常识知识图谱(CKG)中存在的实体及其关系的情况下,对缺失的实体进行预测的任务。现有的方法可以分为生成方法和选择方法两大类。每种方法都有自己的优势。通过理论分析和实证分析,对两种方法进行了比较,发现选择法比生成法更适用于CKGR。在此基础上,进一步结合神经文本编码器的结构和知识图谱嵌入模型,解决了选择方法的两个问题,取得了较好的效果。通过选择方法为后续CKGR任务提供了基本框架和基线模型。

英文摘要:

Commonsense knowledge graph reasoning(CKGR) is the task of predicting a missing entity given one existing and the relation in a commonsense knowledge graph (CKG). Existing methods can be classified into two categories generation method and selection method. Each method has its own advantage. We theoretically and empirically compare the two methods, finding the selection method is more suitable than the generation method in CKGR. Given the observation, we further combine the structure of neural Text Encoder and Knowledge Graph Embedding models to solve the selection method's two problems, achieving competitive results. We provide a basic framework and baseline model for subsequent CKGR tasks by selection methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑