Synthesis Lectures on Human Language Technologies

This book focuses on Entity Discovery and Linking (EDL), which is the problem of identifying concepts and entities, disambiguating them, and grounding them to one or more knowledge bases (KBs). The authors first provide background on the topic and emphasize why it is a crucial step toward understanding natural language text. As most of the content on the internet is not in English, the book also discusses cross-lingual EDL. The authors present the challenges associated with EDL problems and explain the existing solutions. The book covers the core challenges that apply to all EDL problems, as well as the additional challenges associated with cross-lingual EDL problems. The authors also survey relevant research papers, highlight recent trends, and identify areas for future research.