Multimodal Generation in the COMIC Dialogue System
نویسندگان
چکیده
We describe how context-sensitive, usertailored output is specified and produced in the COMIC multimodal dialogue system. At the conference, we will demonstrate the user-adapted features of the dialogue manager and text planner.
منابع مشابه
Multimodal Dialogue Management in the COMIC Project
The next generation internet applications will feature not only the ability to understand spoken and written natural language text, (pen) gestures and body postures, they will also and importantly be able to engage with the user in a natural dialogue about the application. In this paper we will describe the design of a multimodal dialogue and action management module, part of the COMIC demonstr...
متن کاملAssessing the Impact of Adaptive Generation in the COMIC Multimodal Dialogue System
We describe how information from the dialogue history and the user model is incorporated into the output-planning process of the COMIC multimodal dialogue system, and present the results of experiments analysing the impact of both of these factors on the generated descriptions. The results of the experiments confirm and extend previous results by showing that both forms of adaptation make a per...
متن کاملCorpus-Based Planning of Deictic Gestures in COMIC
We describe the recording and annotation of a corpus of roleplaying dialogues in the domain of the COMIC multimodal dialogue system. We give some generalisations about the use of deictic gesture in this task, and show how those findings are currently used in the presentationplanning module of the dialogue system prototype. Finally, we describe how the use of gestures in the system will be evalu...
متن کاملInterleaved Preparation and Output in the COMIC Fission Module
We give a technical description of the fission module of the COMIC multimodal dialogue system, which both plans the multimodal content of the system turns and controls the execution of those plans. We emphasise the parts of the implementation that allow the system to begin producing output as soon as possible by preparing and outputting the content in parallel. We also demonstrate how the modul...
متن کاملA trainable generator for recommendations in multimodal dialog
As the complexity of spoken dialogue systems has increased, there has been increasing interest spoken language generation (SLG). SLG promises portability across application domains and dialogue situations through the development of applicationindependent linguistic modules. However in practice, rulebased SLGs often have to be tuned to the application. Recently, a number of research groups have ...
متن کامل