Adaptive graphical approach to entity resolution

Abstract

Entity resolution is a very common Information Quality (IQ) problem with many different applications. In digital libraries, it is related to problems of citation matching and author name disambiguation; in Natural Language Processing, it is related to coreference matching and object identity; in Web application, it is related to Web page disambiguation. The problem of Entity Resolution arises because objects/entities in real world datasets are often referred to by descriptions, which might not be unique identifiers of these entities, leading to ambiguity. The goal is to group all the entity descriptions that refer to the same real world entities. In this paper we present a graphical approach for entity resolution. It complements the traditional methodology with the analysis of the entity-relationship graph constructed for the dataset being analyzed. The paper demonstrates that a technique that measures the degree of interconnectedness between various pairs of nodes in the graph can significantly improve the quality of entity resolution. Furthermore, the paper presents an algorithm for making that technique self-adaptive to the underlying data, thus minimizing the required participation from the domain-analyst and potentially further improving the disambiguation quality.

A Parallel Computing Method for Entity Recognition based on MapReduce

“…Based on the real data sets, the paper [6] evaluates the efficiency of entity unity. In addition, there are other aspects of the research, like heuristic method [7], distance function [8], Markoff chain [9] and so on. At present, the latest entity recognition method using machine learning [10] algorithm, machine learning library has brought the realization of many classifiers.…”

Video entity resolution: Applying ER techniques for Smart Video Surveillance

“…Over the past few years we have developed a powerful disambiguation engine that we refer to as the Relationshipbased Data Cleaning (RelDC) [3]- [6], [8], [10]. In this section we outline the principal methodology employed by the RelDC framework.…”

“…Further details can be found in [5], [8]. Application of RelDC to the Grouping problem is described in [3], [4].…”

Refining Instance Coreferencing Results Using Belief Propagation

“…This assumption does not hold for scenarios where relevant data is distributed between different instances, which are related to each other. Thus, approaches, which analyze relations between data instances of different classes, have received significant attention in recent years (e.g., [3], [7], [8], [9]). One algorithm focusing on exploiting links between data objects for personal information management was proposed in [3], where the similarities between interlinked entities are propagated using dependency graphs.…”

“…One algorithm focusing on exploiting links between data objects for personal information management was proposed in [3], where the similarities between interlinked entities are propagated using dependency graphs. RelDC [7] proposes an approach based on analyzing entity-relationship graphs to choose the best pair of coreferent entities in case when several options are possible. The authors of these algorithms reported good performance on evaluation datasets and, in particular, significant increase in performance achieved by relation analysis.…”