Use this URL to cite or link to this record in EThOS:
Title: Generating arguments in natural language
Author: Reed, Chris
Awarding Body: University of London
Current Institution: University College London (University of London)
Date of Award: 1999
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Automated generation of persuasive arguments has a wide range of potential applications, but represents a major challenge to existing natural language generation (NLG) techniques. In this thesis, it is argued that existing approaches fall short in several fundamental ways, and that handling argumentation demands major extensions to the conventional NLG model. Five key extensions are discussed. First, a distinction between the logical and rhetorical components of a text is advocated which is reflected in a similar modularisation of the planning task. Second, the adoption of an advanced style of hierarchical planning is proposed which is shown to mirror the hierarchical structure of argument, to increase generative flexibility, and to reduce computational cost. Third, the insufficiencies of a coherence-relation account are enumerated, and employed to motivate a more abstract representation layer drawing on the structural theories developed in argumentation theory. Fourth, conventional models in NLG have represented informational content; more recently, the role of intentional content has been emphasised; here, the importance of the attentional state and its explicit manipulation is also incorporated in a uniform way. Fifth, it is demonstrated that the generation of cue phrases between argument components relies not upon relations holding between clauses, but upon relations between more abstract units of text, and that those cues must necessarily therefore be introduced at an earlier stage of the planning process. An architecture is proposed which integrates these extensions and formalises components of accounts offered in argumentation theory. This formalisation is carried out through a characterisation of deductive, inductive and 'fallacious' argument operators, including Modus Ponens, Modus Tollens, Inductive Generalisation and Ignoratio Elenchi. These argument forms are operationalised (in much the same way as Rhetorical Structure Theory relations have been) as planning operators which employ basic notions not only of belief, but also of saliency. Through a careful analysis of this distinction, argument forms such as the enthymeme, and rhetorical devices such as informing the hearer of facts which he is known already to believe, are shown to be easily accounted for. The architecture is implemented in the Rhetorica system, which encompasses layers of processing responsible for argument structuring and eloquence generation. Rhetorica also employs a body of thirty heuristics, which uniformly represent a variety of the most common guidelines listed in rhetoric and oratory texts of classical, renaissance, Victorian and contemporary authors. The output of the Rhetorica system is a partially ordered plan of primitives which can be refined to lower levels of representation - and in particular, to coherence relation structures. This plan is expressed in a highly parsimonious language involving goals of attention manipulation and saliency, where the latter make reference to the attentional state through a context mechanism. Instances of potentially affect-laden cue phrases of an appropriate class are indicated by saliency goals introduced at the same level of abstraction as the textual units which the cues serve to link. The final plan represents the structure of an argument which, given the available information pertaining to the hearer and other situational factors, maximises both coherency and persuasive effect.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available