Applying Explanation-based Learning to Control and Speeding-up Natural Language Generation

TL;DR

This paper introduces an explanation-based learning approach to automatically extract subgrammars, significantly reducing complexity in natural language generation and enabling system adaptation to specific language uses.

Contribution

It presents a novel EBL-based method for extracting subgrammars that enhances control and efficiency in natural language generation systems.

Findings

Reduces grammatical decision complexity in NLG

Supports adaptation of NLG systems to specific language uses

Improves speed of natural language generation processes

Abstract

This paper presents a method for the automatic extraction of subgrammars to control and speeding-up natural language generation NLG. The method is based on explanation-based learning (EBL). The main advantage for the proposed new method for NLG is that the complexity of the grammatical decision making process during NLG can be vastly reduced, because the EBL method supports the adaption of a NLG system to a particular use of a language.