Semi-structured documents such as web-pages and reports contain text units with complex structure connecting these. We motivate and address the problem of annotating such semi-structured documents using a knowledge gr...
详细信息
ISBN:
(数字)9783030865238
ISBN:
(纸本)9783030865238;9783030865221
Semi-structured documents such as web-pages and reports contain text units with complex structure connecting these. We motivate and address the problem of annotating such semi-structured documents using a knowledge graph schema with entity and relation types. This poses significant challenges not addressed by the existing literature. The latent document structure needs to be recovered, and paths in the latent structure need to be jointly annotated with entities and relationships. We present a two stage solution. First, the most likely document structure is recovered by structure search using a probabilistic graphical model. Next, nodes and edges in the recovered document structure are jointly annotated using a probabilistic logic program, considering logical constraints as well as uncertainty. We additionally discover new entity and relation types beyond those in the specified schema. We perform experiments on real webpage and complex table data to show that our model outperforms existing table and webpage annotation models for entity and relation annotation.
This paper develops a probabilistic-epistemic logicprogram language, PELP, by introducing probabilistic modal operators K-w and PL into LPMLN programs, where w is a sub-interval of [0, 1]. Intuitively, a probabilisti...
详细信息
ISBN:
(纸本)9781538638767
This paper develops a probabilistic-epistemic logicprogram language, PELP, by introducing probabilistic modal operators K-w and PL into LPMLN programs, where w is a sub-interval of [0, 1]. Intuitively, a probabilistic epistemic literal K(w)e denotes that e is known with a probability in w, and a probabilistic comparing literal PL(e(1), e(2)) denotes it is known that the probability of e(1) is less than the one of e(2). The semantics of the new language is based on the semantics of LPMLN and epistemic specifications. In this paper, we analyze the relationship between PELP and some other epistemic logicprogramming languages. We also propose an algorithm for solving PELP programs, and then investigate the application of PELP for modeling and solving the Monty Hall problem and a conformant planning problem with a threshold.
暂无评论