Towards Pragmatic Production Strategies for Natural Language Generation Tasks

TL;DR

This paper introduces a conceptual framework for designing efficient and effective NLG systems that make pragmatic production decisions based on goals, costs, and utility, with applications to grounded referential games and text summarization.

Contribution

It proposes a new framework for NLG system design emphasizing pragmatic decision-making and demonstrates its application to real-world tasks.

Findings

Framework effectively balances production costs and communicative effectiveness.

Application to referential games and summarization shows practical utility.

Encourages learning-based, human-like decision strategies in NLG systems.

Abstract

This position paper proposes a conceptual framework for the design of Natural Language Generation (NLG) systems that follow efficient and effective production strategies in order to achieve complex communicative goals. In this general framework, efficiency is characterised as the parsimonious regulation of production and comprehension costs while effectiveness is measured with respect to task-oriented and contextually grounded communicative goals. We provide concrete suggestions for the estimation of goals, costs, and utility via modern statistical methods, demonstrating applications of our framework to the classic pragmatic task of visually grounded referential games and to abstractive text summarisation, two popular generation tasks with real-world applications. In sum, we advocate for the development of NLG systems that learn to make pragmatic production decisions from experience, by reasoning about goals, costs, and utility in a human-like way.