A syntax-based framework for merging imprecise probabilistic logic programs
Anbu Yue, Weiru Liu · 2009
In this paper, we address the problem of merging multiple imprecise probabilistic beliefs represented as Probabilistic Logic Programs (PLPs) obtained from multiple sources. Beliefs in each PLP are modeled as conditional events attached with prob-ability bounds. The major task of syntax-based merging is to obtain the most rational probability bound for each conditional event from the original PLPs to form a new PLP. We require the minimal change principle to be followed so that each source gives up its beliefs as little as possible. Some in-stantiated merging operators are derived from our merging framework. Furthermore, we propose a set of postulates for merging PLPs, some of which ex-tend the postulates for merging classical knowledge bases, whilst others are specific to the merging of probabilistic beliefs. 1