We are transitioning from the era of Big Data to Big Knowledge,
and semantic knowledge bases such as knowledge graphs play an
important role in this transition. This is evident from the increased
investments in Knowledge Graph research and development by
major industrial players resulting in widely used systems such as
IBM's Watson, Google's entity search, Apple's Siri, and Amazon's
Knowledge Graphs can be constructed either manually (facts authored by humans) or automatically (facts extracted from text using Machine Learning tools). Manually curated knowledge graphs such as DBpedia, YAGO, etc. have little or no noisy facts as they are carefully authored, but they require very large human efforts. This problem is further exacerbated in enterprise domains and custom domains such as life sciences, finance, intelligence, etc. where domain expertise is also crucial to add good quality facts in the graph. As a result, efforts have been made for development of systems for automatic construction of semantic knowledge bases for domain specific corpora and systems that use such domain specific knowledge bases are gaining prominence.
Through the proposed tutorial, we aim to cover the state-of-the-art approaches in Knowledge Graph Construction from various types of data (i.e. unstructured, semi structured and structured data) using both manual as well as automated methods. We also wish to review applications from various disciplines that benefit from the structure and semantics offered by knowledge graphs. Lastly, we will present case studies describing our experiences in construction of enterprise Knowledge Graphs and their applications in life sciences and intelligence domains.
Part 1: Background and KG Construction,
Part 2: Knowledge Graph Analytics and Applications
Knowledge Graphs and Information Retrieval: A Symbiotic Relationship (Version presented at FIRE, 2018).