A growing number of research projects both in academia and industries have started to investigate the use of animated agents in the interface. Such agents, either based on real video, cartoon-style drawings or even model-based 3D graphics, are likely to become integral parts of future user interfaces. To be useful, however, interface agents have to be intelligent in the sense that they exhibit a reasonable behavior. In this paper, we present a system that uses a lifelike character, the so-called PPP Persona, to present multimedia material to the user. This material has been either automatically generated or fetched from the web and modified if necessary. The underlying approach is based on our previous work on multimedia presentation planning. This core approach is complemented by additional concepts, namely the temporal coordination of presentation acts and the consideration of the human-factors dimension of the added visual metaphor.

Computer-based presentation systems enable the realization of effective and dynamic presentation styles that incorporate multiple media. Obvious examples are animated user interface agents which verbally comment on multimedia objects displayed on the screen while performing cross-media and cross-window pointing gestures. The design of such presentations must account for the temporal coordination of media output and the agent's behavior. In this paper we describe a new presentation system which not only creates the multimedia objects to be presented, but also generates a script for presenting the material to the user. In our system, this script is forwarded to an animated presentation agent running the presentation. The paper details the kernel of the system which is a component for planning temporally coordinated multimedia. Introduction The success of human-human communication undisputably depends on the rhetorical and didactical skills of the speaker or presenter. Surprisingly enoug...

Life-like characters are increasingly gaining the attention of researchers and commercial developers of user interfaces. A strong argument for using characters in the interface is that they enrich the repertoire of available options which allow to emulate more familiar communication styles for interacting with a computer. The focus of our work is on lifelike presentation agents. In this contribution, we present a framework for the development of presentation agents which can be utilized for a broad range of applications including personalized information delivery from the WWW.

The acceptance of natural language generation systems strongly depends on their capability to facilitate the exchange of information with human users. Current generation systems consider the influence of situational factors on the content and the form of the resulting utterances. However, the need to time their processing flexibly is usually neglected although temporal factors play a central part when directly addressing a human communication partner. A short response time of a system is crucial for its effective use. Furthermore, some applications --- e.g., the simultaneous description of ongoing events --- even necessitate the interleaving of input consumption and output production, i.e. the use of an incremental processing mode. We claim that incremental processing is a central design principle for developing flexible and efficient generators for speech output. We discuss the advantages of parallel processing for incremental generation and several aspects of control of the generator...

Abstract. The automated generation of multimedia reports for timevarying scenes on the basis of visual data constitutes a challenging research goalwith a high potential for many interesting applications. In this paper, we report on our work towards an automatic commentator system for RoboCup, the Robot World-Cup Soccer. Rocco (RoboCup-Commentator) is a prototype system that has emerged from our previous work on high-level scene analysis and intelligent multimedia generation. Based on a general conception for multimedia reporting systems, we describe the initial Rocco version which isintended to generate TV-style live reports for matches of the simulator league. 1

Abstract. The integration of vision and natural language processing increasingly attracts attention in different areas of AI research. Up to now, however, there have only been a few attempts at connecting vision systems with natural language access systems. Within the SFB 314, special collaborative program on AI and knowledge-based systems, the automatic natural language description of real world image sequencesconstitutes a major research goal, which has been pursued during the last ten years. The aim of our approach is to obtain an incremental evaluation and simultaneous description of the perceived time-varying scenes. In this contribution we will report on new results of our joint efforts at combining the natural language access system VITRA with a vision system. We have investigated the problem of describing the movements of articulated bodies in image sequences within an integrated natural language and computer vision system. The paper will focus on our model-based approach for the recognition of pedestrians and on the further evaluation and language production in VITRA. 1

This paper deals with the reference choices involved in the generation of argumentative text. Since a natual segmentation of discourse into attentional spaces is needed to carry out this task, this paper first proposes an architecture for natural language generation that combines hierarchical planning and focus-guided navigation, a work in its own right. While hierarchical planning spans out an attentional hierarchy of the discourse produced, local navigation fills details into the primitive discourse spaces. The usefulness of this architecture actually goes beyond the particular domain of application for which it is developed. A piece of argumentative text such as the proof of a mathematical theorem conveys a sequence of derivations. For each step of derivation, the premises derived in the previous context and the inference method (such as the application of a particular theorem or definition) must be made clear. Although not restricted to nominal phrases, our reference decisions are similar to those concerning nominal subsequent referring expressions. Based on the work of Reichmann, this paper presents a discourse theory that handles reference choices by taking into account both textual distance as well as the attentional hierarchy.

Unlike conventional printed text which allows for passive viewing only, computer-based presentations can support various forms of user interaction and enable the user to play an active role during the presentation. As each presentation style has its own strengths and weaknesses, we aim at an automated multimedia presentation system that is not only able to choose among different presentation styles, but also offers the user the possibility to flexibly switch between them. When tackling typical problems arising in a hypermedia discourse, such as navigation issues, coherent continuation of presentations, establishing crossmedia links and guided explorations, the need for a suitable representation of the discourse structure becomes apparent. This paper aims at making two contributions. First, it provides a communication theoretical structuring approach which allows for the description of the contents of presentation parts, the relations between them and user interaction within a uniform f...

Natural language generation must work with insufficient input. Underspecifications can be caused by shortcomings of the component provkling the input or by the preliminary state of incrementally given input. The paper Mms escape from such dead-end situ,tions by making kssumptions. We discuss global aspects of default lmndling. Two problem classes for deftmits in the incremental syntactic gonor;[tor VM-GI]N m'e presented to substantiate our discusskin.

Obviously, human speech comprehension works in an incremental way: Unbiased introspection as well as evidence from psycholinguistics strongly suggest that we start to recognize a word before it has been completely uttered; even more, we may interrupt our conversation partner at that point if we disagree with what we think (s)he will be saying. Thus, incrementality is not restricted to any particular level of human speech comprehension, but is a general principle that is valid for all levels of processing --- thus making simultaneous interpretation possible. From a more technical point of view, incrementality would offer several advantages when constructing a machine interpretation system. The enormous processing amount that is necessary to cope with e.g. input consisting of continuous and spontaneous speech can partially be reduced by means of incremental processing. There have been several investigations on the use of incrementality for natural language understanding at various levels...