Natural Language Data Management and Interfaces (Synthesis Lectures on Data Management)

The volume of natural language text data has been rapidly increasing over the past two decades, due to factors such as the growth of the Web, the low cost associated with publishing, and the progress on the digitization of printed texts. This growth combined with the proliferation of natural language systems for search and retrieving information provides tremendous opportunities for studying some of the areas where database systems and natural language processing systems overlap.

This book explores two interrelated and important areas of overlap: (1) managing natural language data and (2) developing natural language interfaces to databases. It presents relevant concepts and research questions, state-of-the-art methods, related systems, and research opportunities and challenges covering both areas. Relevant topics discussed on natural language data management include data models, data sources, queries, storage and indexing, and transforming natural language text. Under natural language interfaces, it presents the anatomy of these interfaces to databases, the challenges related to query understanding and query translation, and relevant aspects of user interactions. Each of the challenges is covered in a systematic way: first starting with a quick overview of the topics, followed by a comprehensive view of recent techniques that have been proposed to address the challenge along with illustrative examples. It also reviews some notable systems in details in terms of how they address different challenges and their contributions. Finally, it discusses open challenges and opportunities for natural language management and interfaces.

The goal of this book is to provide an introduction to the methods, problems, and solutions that are used in managing natural language data and building natural language interfaces to databases. It serves as a starting point for readers who are interested in pursuing additional work on these exciting topics in both academic and industrial environments.

Yunyao Li is a Senior Research Manager and Research Staff Member with IBM Research - Almaden. She is also a Master Inventor and a member of IBM Academy of Technology. Her expertise is in the interdisciplinary areas of databases, natural language processing, human-computer interaction, machine learning, and information retrieval. Her contributions in these areas have led to over 50 research publications, more than 20 patents granted or filed, multiple graduate-level courses (including 2 Massive Open Online Courses), and billions of revenue generated from technology transfer. She is widely recognized in these areas both within IBM and by the external research community, and regularly serves on prestigious program committees, editorial boards, and review panels. Her current research interest focuses on taming unstructured and semi-structured content to enable the building of new generations of AI applications for the enterprise. Yunyao is also passionate about improving the diversity for the STEM field. She has been actively mentoring women and under-represented minorities for over ten years. She received her Ph.D. and master’s degrees from the University of Michigan, Ann Arbor and undergraduate degrees from Tsinghua University, Beijing, China.