Text generation: using discourse strategies and focus constraints to generate natural language text
Text generation: using discourse strategies and focus constraints to generate natural language text
Using argumentation to control lexical choice: a functional unification implementation
Using argumentation to control lexical choice: a functional unification implementation
Real versus Template-Based Natural Language Generation: A False Opposition?
Computational Linguistics
A survey on question answering technology from an information retrieval perspective
Information Sciences: an International Journal
Hi-index | 0.00 |
This paper is a study on constructing a natural language interface to relational databases, which accepts natural language questions as inputs and generates textual responses. The question is translated into a SQL query using a semantic grammar and then, a database management system is left to find the result table with its own specialized optimization and planning techniques. The textual responses are generated from the result table based on another semantic grammar and the query type. Experimental results show that this approach can analyze a wide range of questions with high accuracy and produce reasonable textual responses.