Elisabeth Maier

How to implement a naturalistic model of abstracting: four core working steps of an expert abstractor

Abstract Four working steps taken from a comprehensive empirical model of expert abstracting are studied in order to prepare an explorative implementation of a simulation model. It aims at explaining the knowledge processing activities during professional summarizing. Following the case-based and holistic strategy of qualitative empirical research, we develop the main features of the simulation system by investigating in detail a small but central test case—four working steps where an expert abstractor discovers what the paper is about and drafts the topic sentence of the abstract. Following the KADS methodology of knowledge engineering, our discussion begins with the empirical model (a conceptual model in KADS terms) and aims at a computational model which is implementable without determining the concrete implementation tools (the design model according to KADS). The envisaged solution uses a blackboard system architecture with cooperating object-oriented agents representing cognitive strategies and a dynamic text representation which borrows its conceptual relations in particular from RST (Rhetorical Structure Theory). As a result of the discussion we feel that a small simulation model of professional summarizing is feasible.

Employing Knowledge Resources in a New Text Planner Architecture

We describe in this paper a new text planner that has been designed to address several problems we had encountered in previous systems. Motivating factors include a clearer and more explicit separation of the declarative and procedural knowledge used in a text generation system as well as the identification of the distinct types of knowledge necessary to generate coherent discourse, such as communicative goals, text types, schemas, discourse structure relations, and theme development patterns. This knowledge is encoded as separate resources and integrated under a flexible planning process that draws from appropriate resources whatever knowledge is needed to construct a text. We describe the resources and the planning process and illustrate the ideas with an example.

Structuring collaborative information-seeking dialogues

Conversational approaches to human—computer collaboration have so far mostly been employed for the design of natural language interfaces. It is claimed, however, that the conversational interaction model described in the paper can also feasibly be applied to graphical and multimodal interactions. The model comprises two interrelated parts: first, the description of local discourse structures and functional interrelations between dialogue acts to capture (local) conversational tactics, and second, the description of global structures by so-called dialogue scripts which are related to (global) information-seeking strategies. The application of the model in a multi-media information retrieval system is described in the conclusions to the paper.

Generating cooperative system responses in information retrieval dialogues

This paper describes the Corinna system which integrates a theoretical approach to dialogue modeling with text generation techniques to conduct cooperative dialogues in natural language. It is shown how the dialogue model COR can be augmented by adding discourse relations as an additional level of description which is particularly valuable for the generation of dialogue acts.

Textual Relations as Part of Multiple Links Between Text Segments

Many text planning systems are based on a theoretical linguistic approach which assumes the existence of relations between units of text. The relational approach most extensively used in text generation is the Rhetorical Structure Theory (rst, Mann and Thompson 1987). The phenomenon of multiple relations, i.e. the fact that in natural language texts we often find more than one relation holding between two text units, has not been treated by rst. In this paper we show how the taxonomy of discourse structure relations as proposed in Maier and Hovy (1991) can be exploited to account for a subtype of multiple relations. We also give an outline of a computational model to generate texts including multiple relations.