In this paper, we describe an architecture for conversational systems that enables human-like performance along several important dimensions. First, interpretation is incremental, multi-level, and involves both general and task- and domainspecific knowledge. Second, generation is also incremental, proceeds in parallel with interpretation, and accounts for phenomena such as turn-taking, grounding and interruptions. Finally, the overall behavior of the system in the task at hand is determined by the (incremental) results of interpretation, the persistent goals and obligations of the system, and exogenous events of which it becomes aware. As a practical matter, the architecture supports a separation of responsibilities that enhances portability to new tasks and domains.

This paper describes the linguistic part of a system called PROVERB, which transforms, abstracts, and verbalizes machine-found proofs into formated texts. Linguistically, the architecture of PROVERB follows most application oriented systems, and is a pipe-lined control of three components. Its macroplanner linearizes a proof and plans mediating communicative acts by employing a combination of hierarchical planning and focus-guided navigation. The microplanner

This article presents a new semanticbased transfer approach developed and applied within the Verbmobil Machine Translation project. We give an overview of the declarative transfer fo,'malism to- gether with its procedural realization. Our approach is discussed and compared with several other approaches f,'om the MT literature. The results presented in this article have been implemented and integrated into the Verbmobil system.

This paper outlines the interactive proof explanation system P.rex, which adapts its explanation to the user and allows him anytime to utter questions or requests, to which it reacts flexibly. As a generic system, it can be connected to different theorem provers. The distribution is available via the P.rex home page at http://www.ags.uni-sb.de/~prex.

This report presents a summary of the architectural characteristics of some of the Natural Language Generation (NLG) systems that serve as the main building blocks of the RAGS

This paper describes a fully incremental dialogue system that can engage in dialogues in a simple domain, number dictation. Because it uses incremental speech recognition and prosodic analysis, the system can give rapid feedback as the user is speaking, with a very short latency of around 200ms. Because it uses incremental speech synthesis and self-monitoring, the system can react to feedback from the user as the system is speaking. A comparative evaluation shows that naïve users preferred this system over a non-incremental version, and that it was perceived as more human-like. 1 1

We argue in this paper that sophisticated microplanning techniques are required even for mathematical proofs, in contrast to the belief that mathematical texts are only schematic and mechanical. We demonstrate why paraphrasing and aggregation significantly enhance the flexibility and the coherence of the text produced. To this end, we adopted the Text Structure of Meteer as our basic representation. The type checking mecha- nism of Text Structure allows us to achieve paraphrasing by building comparable combinations of linguistic resources. Specified in terms of concepts in an uniform ontological structure called the Upper Model, our semantic aggregation rules are more compact than similar rules reported in the literature.

Abstract. This article gives an overview of a new semantic-based transfer approach developed and applied within the Verbmobil Machine Translation project [22]. We present the declarative transfer formalism and discuss its implementation. The results presented in this paper have been integrated successfully in the Verbmobil system. 1

We argue that .the current, predominantly task-oriented, approaches to modularizing text 'generation, While plausible and useful conceptually, set up spurious conceptual and operational constraints. We propose a data-driven approach to modularization and illustrate how it eliminates.

In order to generate high quality explanations in mathematical domains, the presentation must be adapted to the knowledge of the intended audience. Most proof presentation systems only communicate proofs on a fixed degree of abstraction independently of the addressee's knowledge. In this paper, we shall present the proof explanation system P.rex. Based on assumptions about the addressee's knowledge, its dialog planner chooses a degree of abstraction for each proof step to be explained. In reaction to the user's interactions, which are allowed at any time, it enters clarification dialogs to revise its user model and to adapt the explanation. 1