Using centering theory to plan coherent texts

This paper describes an approach to text planning, one of the distinct tasks iden-tiied in Ehud Reiter's \consensus" architecture for Natural Language Generation (Reiter 1994, Reiter and Dale 1997). This consists a \pipeline" of distinct tasks: Text Planning-deciding the content of a message, and organising the component propositions into a text tree; Sentence Planning-aggregating propositions into clausal units and choosing lexical items corresponding to concepts in the knowledge base; Linguistic realisation-surface details such as agreement, orthography etc. (See also (Cahill et al. 1999) who propose a more elaborate model which allows the \pipeline" as a concrete instantiation.) We assume that the component propositions to be realised in a text are organised in a tree structure in which terminal nodes are elementary propositions and non-terminal nodes represent discourse relations as deened by e.g., Rhetorical Structure Theory (RST, Mann and Thompson 1987). This structure only partially determines the linear order in which the propositions will be realised-in other words, any RST structure speciies a range of possible text plans. We propose as an additional constraint that the generator should seek to maximise continuity of reference as determined by the rules and constraints of centering theory, and we argue that this enables us to select the most cohesive variants from a set of text plans. 2 Centering in a nutshell Centering theory (CT) is a theory of discourse structure which models the interaction of cohesion and salience in the internal organisation of a text. (See Grosz et al 1995; cf Hardt 1998 for a more formal treatment.) The main assumptions of the theory are: 1. For each utterance in a discourse there is precisely one entity which is the centre of attention or center. The center in an utterance U n is the most grammatically salient entity realised in U n?1 which is also realised in U n. This is also referred to as the backward-looking center or Cb. 2. There is a preference for consecutive utterances within a discourse segment to keep the same entity as the center, and for the center to be realised as Subject or preferred center (Cp). We refer to these principles as cohesion and salience 1 respectively. (Hardt's (1998) formalization only covers the rst of these.) Pairs of successive utterances hU n ; U n+1 i are classiied into the transition types shown in Fig. 1, in order of preference. 3. The center is the entity which …