Michigan Researchers Win Best Paper Award at VLDB 2015
The paper proposes an interactive natural language interface for relational databases, which enables novice users to construct complex queries.
Prof. H.V. Jagadish, the Bernard A. Galler Collegiate Professor of Electrical Engineering and Computer Science, and CSE graduate student Fei Li have received the Best Paper Award at the 41st International Conference on Very Large Data Bases, which took place Aug 31st – Sept 4th in Kohala Coast, Hawaii.
Their paper entitled Constructing an Interactive Natural Language Interface for Relational Databases, proposes an interactive natural language interface for relational databases, which enables novice users to construct complex queries. It improves the usability of an RDBMS, as it enables anyone to ask questions of a database system.
For a query expressed in natural language, the interface interacts with the user in several steps in determining the query semantics and subsequently generating the corresponding SQL. At each step, the system interactively presents to the user its own understanding of the query through alternatives, as opposed to just final answers. The authors rely on a query tree structure to represent the interpretation of an NLP query from the database’s perspective, which facilitates verification by users, and translation in SQL.
The system was implemented following the component-based approach, where each component can be independently constructed, optimized or substituted. The experiments involve real users and verify the feasibility of the approach and illustrate the strengths of the system/approach.
Fei Li is a PhD candidate and is a member of the Database Group. His research interests focus on Database Usability, especially, how to enable non-technical users to compose logically complex queries. He is advised by Prof. Jagadish.
Prof. H.V. Jagadish is well known for his broad-ranging research on database systems, data mining, and the use of big data. He is widely recognized for his pioneering work on multi-dimensional data, and for developing new representation techniques and indexing schemes to store and retrieve non-conventional data sets such as geometric objects and text. He received his PhD from Stanford in 1985 and joined the faculty at Michigan in 1999. He is a member of the Database Group at Michigan, a fellow of ACM, and a distinguished scientist at the Michigan Institute for Data Science.