Correcting Inconsistencies through Association Rules in Temporal Large Growing Knowledge Bases
2017 Brazilian Conference on Intelligent Systems (BRACIS)(2017)
摘要
Large Knowledge Bases construction has been a relevant topic in the last years. Most techniques focus on discovering facts or relations like presidentOf(Bush, United_States). Many of them are associated with a specific temporal scope, thus, they are true only for a specific period of time. Therefore, a fact (e.g. presidentOf (Bush, United_States)) that was true in the past, might not be currently true anymore. Moreover, automatically (or semi-automatically) created large knowledge bases tend to have noise and inconsistencies, and trying to identify and correct them are quite important. To detect an inconsistency, two probabilistic metrics were developed based on the punctuality of the specific temporal association rules discovered. After detecting the inconsistencies, it is possible to correct them (i) manually or (ii) using Conversing Learning. Experiments showed that our probabilistic metrics can help detecting inconsistencies in large growing knowledge bases aswell as how they are fixed.
更多查看译文
关键词
Specific Temporal Association Rules,Large Knowledge Bases,Inconsistency Detection
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络