A Computational Model for Generating Referring Expressions in a Multilingual Application Domain

In this paper we analyse the problem of generating referring expressions in a multilingnal generation system that produces instructions on how to fill out pension forms. The model we propose is an implementation of the theoretical investigations of Martin and is based on a clear representation of the knowledge sources and choices that contribute to the identification of the most appropriate linguistic expressions. To cope effectively with pronominalization we propose to augment the Centering Model with mechanisms exploiting the discourse structure. At every stage of the referring expressions generation process issues raised by multilinguality are considered and dealt with by means of rules customized with respect to the output language. 1 Introduction An automatic generation system that is to produce good quality texts has to include effective algorithms for choosing the linguistic expressions referring to the domain entities. The expressions have to allow the reader to easily identify the referred objects, avoiding ambiguities and unwanted implications. They have to conform to the expectations of the reader according to his evolving flow of attention and they have to contribute to the cohesion of the text. In this paper, we describe a component, developed inside the GIST project 1, building referring 1The GIST consortium includes academic and in-plutense de Madrid (Spain)-as well as two user groups collaborating actively to the specification and evaluation of the system-INPS (the Italian National Security Service) and the Autononm Province of Bolzano. expressions for automatically generated multilin-gum (English, German, Italian) instructions in the pension domain. The overall decision making mechanism for the referring expressions choices is based on the theoretical investigations of Martin (Martin, 1992), for which we propose a possible implementation. The implemented model proved to be particularly suitable to work in a multilin-gum domain. For the generation of pronouns we define an extension of the Centering Model exploiting the contextual information provided by the rhetorical structure of discourse (Not and Zan-canaro, 1996). At every stage of the referring expressions generation process issues raised by multilinguality are considered and dealt with by means of rules cus-tomized with respect to the language. In section 2 we first present the results of observations made on the corpus texts with the aim of identifying the typical referring expressions occurring in our domain. Section 3 details the solutions implemented in the GIST system. Specifications for the implementation are given in terms of data structures and required algorithms. 2 Referring expressions …