Mapping Natural Language into SQL in a NLIDB

Authors:
Alessandra Giordani
Affiliations:
University of Trento, Povo di Trento, Italy
Venue:
NLDB '08 Proceedings of the 13th international conference on Natural Language and Information Systems: Applications of Natural Language to Information Systems
Year:
2008

Citing 6
Cited 1

Towards a theory of natural language interfaces to databases

Proceedings of the 8th international conference on Intelligent user interfaces
Spanish Natural Language Interface for a Relational Database Querying System

TSD '02 Proceedings of the 5th International Conference on Text, Speech and Dialogue
NaLIX: an interactive natural language interface for querying XML

Proceedings of the 2005 ACM SIGMOD international conference on Management of data
MASQUE/SQL: an efficient and portable natural language query interface for relational databases

IEA/AIE'93 Proceedings of the 6th international conference on Industrial and engineering applications of artificial intelligence and expert systems
Automatic learning of textual entailments with cross-pair similarities

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Issues in translating from natural language to SQL in a domain-independent natural language interface to databases

MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence

Naturalistic types

Proceedings of the 10th SIGPLAN symposium on New ideas, new paradigms, and reflections on programming and software

Quantified Score

Hi-index	0.00

Visualization

Abstract

Since the 1970's, there has been growing interest in understanding and answering human language questions. Despite this, little progress has been made in developing an interface that any untrained user can use to query very large databases using natural language. In this research, the design of a novel system is discussed. Tree-like structures are built for every question and each query, and a tree kernel, which represents trees in terms of their substructures, is used to define feature spaces. A machine learning algorithm is proposed that takes pairs of trees as training input and derives the unknown final SQL query by matching propositional and relational substructures.