PROJECT TITLE :

Profiling Entities over Time in the Presence of Unreliable Sources - 2017

ABSTRACT:

To harness the wealthy amount of knowledge offered on the web today, several organizations aggregate public (and private) knowledge to derive information repositories for real-world entities. This paper aims to make historical profiles of real-world entities by integrating temporal records collected from totally different sources. This drawback is challenging not only as a result of entities could amendment their attribute values over time, however conjointly as a result of data provided by the sources may be unreliable. In this paper, we gift a new resolution for profiling entities over time. To understand the evolution of entities, we describe a novel transition model that offers the probability that an entity can modification to a particular attribute value once some time period. Next, a group of quality metrics are defined for the data sources to capture the exactness and timeliness of their provided values. The transition model and the standard metrics are then engineered into a source-aware temporal matching algorithm that may link temporal records to entities at the proper time and augment entity profiles with correct values. Our suite of experiments demonstrate that the proposed approach is in a position to outperform the state-of-the-art techniques by constructing additional complete and correct profiles for entities.