Artificial Intelligence (AI) based Entity Resolution & Information Quality (ERIQ)

Entity Resolution has been an important field of study for many researchers for decades. The most common use of entity resolution has been “pairwise matching”. To enable such combination of human effort with some software help has been successful. However, traditional methods used in the past were dependent on the human effort. Such efforts are time consuming, laborious, and lack the ability to produce quick summaries on large sets of data. In addition, human efforts to identify duplicates from very large data sets are often prone to errors.

Since manually managing data records linkages is inefficient and prone to errors, in recent years, researchers have applied the use of machine learning, supervised and unsupervised training, to study the impact of linking records, de-duplication, and reduce human effort for better entity resolution. In most recent years, researchers have explored the application of machine learning and deep learning to improve F-measures. These efforts helped to improve entity resolution for structured and semi-structured references. However, entity resolution for “unstructured references” continues to be a challenging task.

Data Quality, Governance, and Policy Management using Deep Learning

More Coming Soon

Send an email to to info@eriq.ai to stay updated with our latest news.