An ascription-based approach to speech acts

TL;DR

This paper introduces a novel belief modelling technique for speech act processing that propagates nested beliefs on demand, improving upon previous simplistic models and enhancing dialogue understanding.

Contribution

It presents an ascription-based approach that allows dynamic propagation of nested beliefs, advancing speech act processing in dialogue systems.

Findings

Demonstrates improved handling of nested beliefs in dialogue

Enhances speech act recognition accuracy

Provides a flexible belief modelling framework

Abstract

The two principal areas of natural language processing research in pragmatics are belief modelling and speech act processing. Belief modelling is the development of techniques to represent the mental attitudes of a dialogue participant. The latter approach, speech act processing, based on speech act theory, involves viewing dialogue in planning terms. Utterances in a dialogue are modelled as steps in a plan where understanding an utterance involves deriving the complete plan a speaker is attempting to achieve. However, previous speech act based approaches have been limited by a reliance upon relatively simplistic belief modelling techniques and their relationship to planning and plan recognition. In particular, such techniques assume precomputed nested belief structures. In this paper, we will present an approach to speech act processing based on novel belief modelling techniques where nested beliefs are propagated on demand.