Incremental Knowledge Base Construction Using DeepDive
This work addresses the iterative process of populating databases from unstructured data, offering significant efficiency gains for KBC systems in industry and research, though it is incremental in nature.
The paper tackles the problem of incremental knowledge base construction (KBC) by developing DeepDive, a system that uses sampling and variational techniques for efficient inference, resulting in speedups of up to two orders of magnitude with minimal quality loss.
Populating a database with unstructured information is a long-standing problem in industry and research that encompasses problems of extraction, cleaning, and integration. Recent names used for this problem include dealing with dark data and knowledge base construction (KBC). In this work, we describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems, and we present techniques to make the KBC process more efficient. We observe that the KBC process is iterative, and we develop techniques to incrementally produce inference results for KBC systems. We propose two methods for incremental inference, based respectively on sampling and variational techniques. We also study the tradeoff space of these methods and develop a simple rule-based optimizer. DeepDive includes all of these contributions, and we evaluate DeepDive on five KBC systems, showing that it can speed up KBC inference tasks by up to two orders of magnitude with negligible impact on quality.