Mitigating linked data quality issues in knowledge-intense information extraction methods

Abstract

Advances in research areas such as named entity linking and sentiment analysis have triggered the emergence of knowledge-intensive information extraction methods that combine classical information extraction with background knowledge from the Web. Despite data quality concerns, linked data sources such as DBpedia, GeoNames and Wikidata which encode facts in a standardized structured format are particularly attractive for such applications.This paper addresses the problem of data quality by introducing a framework that elaborates on linked data quality issues relevant to di erent stages of the background knowledge acquisition process, their impact on information extraction performance and applicable mitigation strategies. Applying this framework to named entity linking and data enrichment demonstrates the potential of the introduced mitigation strategies to lessen the impact of di erent kinds of data quality problems. An industrial use case that aims at the automatic generation of image metadata from image descriptions illustrates the successful deployment of knowledge-intensive information extraction in real-world applications and constraints introduced by data quality concerns.

Classifying News Media Coverage for Corruption Risks Management with Deep Learning and Web Intelligence

“…The Integrity Risks Monitor draws upon documents obtained from popular Austrian, German, Swiss, U.K. and U.S. media outlets that are pre-processed, analyzed and semantically enriched using methods such as part-of-speech tagging, dependency parsing [21], sentiment analysis [18], keyword analysis [20] and named entity linking [19]. In addition, we assign a score to each document that indicates its likelihood to contain coverage on integrity risks.…”

Mining and Leveraging Background Knowledge for Improving Named Entity Linking

“…Ristoski and Paulheim [19] suggest to deal with data problems in a separate data preprocessing step that handles missing values, identifies incorrect data, eliminates duplicates and performs conflict resolution. Weichselbraun and Kuntschik [29] discuss the impact of these data quality issues on knowledge extraction methods and investigate different mitigation strategies for the corresponding dimensions. They suggest to integrate these strategies into graph mining and information extraction methods and provide real-world use cases of such mitigation strategies.…”

Assessment of Knowledge and Practices of Community Health Nurses on Data Quality in the Ho Municipality of Ghana

“…This high-quality healthcare data offers potential value for optimizing care delivery, but it is still perceived as a by-product of healthcare delivery, rather than a central asset source for competitive advantages [3]. Quality data, particularly concerning timeliness, completeness and accuracy are needed for a variety of purposes including health sector reviews, planning, programme monitoring, quality improvement and reporting [2] [4]. For this reason, it is critical to have high-quality data on performance in the health sector available routinely [2].…”