A Model of Natural Language Dialogue

Gravett, John (1993). A Model of Natural Language Dialogue. MPhil thesis The Open University.

DOI: https://doi.org/10.21954/ou.ro.0000ff10


In this thesis I have a threefold purpose. Firstly, I will attempt to argue that the individual utterances agents make in natural language dialogue stem from specific beliefs, goals, and plans and that these interlock with those of other agents in the production of dialogue. I suggest that agents utilise syntactic, semantic, pragmatic and contextual knowledge in this process. Furthermore, that these elements contribute to the utterances speakers make and hearers interpret in the pursuit of their individual goals, and cannot be treated separately. I will suggest that utterances, being intentional behaviour, are sub-components of plans to achieve specific communicative purposes. Following from this, I will present a descriptive model showing how the beliefs and goals of agents contribute to the composing of a logical form for an utterance prior to its syntactic representation. It is suggested that the logical form of an utterance, is composed of elements relating to the agent's beliefs and goals, and includes pragmatic and contextual elements and that these are present prior to the utterance being made and predispose the choice of eventual syntactic components. I do not attempt to model the syntactic form of the utterances but limit the model of the agents to a display to each other of their logical forms and show how these might be interpreted and elicit responses from the hearer in furtherance of their goals. My third purpose is to present a hand-simulated process of this model, to demonstrate how a particular dialogue might be constructed by two agents. This is attempted by ascribing a set of beliefs to them and providing them with specific goals. In the final chapter, the achievements and inadequacies of this research are summarised, and possible improvements and developments suggested in the context of current and future directions.

Viewing alternatives

Download history


Public Attention

Altmetrics from Altmetric

Number of Citations

Citations from Dimensions

Item Actions