Natural language database access using semi-automatically constructed translation knowledge

Authors:
In-Su Kang;Jae-Hak J. Bae;Jong-Hyeok Lee
Affiliations:
Div. of Electrical and Computer Engineering, POSTECH and AITrc, Pohang, Republic of Korea;School of Computer Engineering and Information Technology, University of Ulsan, Republic of Korea;Div. of Electrical and Computer Engineering, POSTECH and AITrc, Pohang, Republic of Korea
Venue:
IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing
Year:
2004

Citing 8
Cited 0

Communicating with databases in natural language

Communicating with databases in natural language
Problems and some solutions in customization of natural language database front ends

ACM Transactions on Information Systems (TOIS)
TEAM: an experiment in the design of transportable natural-language interfaces

Artificial Intelligence
The vocabulary problem in human-system communication

Communications of the ACM
Developing a natural language interface to complex data

ACM Transactions on Database Systems (TODS)
An English language question answering system for a large relational database

Communications of the ACM
Introduction to Modern Information Retrieval

Introduction to Modern Information Retrieval
An efficient easily adaptable system for interpreting natural language queries

Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In most natural language database interfaces (NLDBI), translation knowledge acquisition heavily depends on human specialties, consequently undermining domain portability. This paper attempts to semi-automatically construct translation knowledge by introducing a physical Entity-Relationship schema, and by simplifying translation knowledge structures. Based on this semi-automatically produced translation knowledge, a noun translation method is proposed in order to resolve NLDBI translation ambiguities.