IIIT Hyderabad Publications |
|||||||||
|
A Novel Approach to Aggregation Processing in Natural Language Interfaces to DatabasesAuthors: Abhijeet Gupta,Rajeev Sangal Conference: The 10th International Conference on Natural Language Processing (ICON-2013 2013) Date: 2013-12-18 Report no: IIIT/TR/2013/119 AbstractIn aggregations, a function is applied to a set of values or entities in a database to yield a single value. Databases use a limited set of inbuilt functions to perform aggregations, hence, restricting NLIDB systems in processing domain based complex aggregations. In this paper, we introduce an aggregation processing framework, which can handle different types of aggregation operations in a natural language query, including direct quantitative as well as indirect qualitative aggregations, and those which combine quantifiers or relational operators with aggregations. Equally importantly, this is done as a separate layer independent of the processing capability in SQL, database query language. The framework has two distinct stages of processing. In the first stage, aggregations are performed on a data stream, and in the second stage the data stream can be further filtered, if required, on the result obtained in the first stage. With our approach, we have achieved an accuracy of 98.1% in processing aggregations and dealt with certain issues arising due to aggregations in SQL queries. Full paper: pdf Centre for Language Technologies Research Centre |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |