Learning dialogue management models poses significant challenges. In a complex taskoriented domain in which information is exchanged via parallel, interleaved dialogue and task streams, effective dialogue management models should be able to make dialogue moves based on both the dialogue and the task context. This paper presents a data-driven approach to learning dialogue management models that ...

Currently the performance of dialogue system is mostly mearsured based on the analysis of a large dialogue corpus. In this way, the dialogue performance can not be obtained before the system is on line, and the dialogue corpus should be recollected if the system is modified. Also, the effect of different factors, including system’s dialogue strategy, recognition and understanding accuracy or us...

[1] Records of Pa/Th from Atlantic sediments have been interpreted to reflect changes in ocean circulation during the geologic past. Such interpretations should be tested with due regard to the limited spatial coverage of Pa/Th data and the uncertainties in our current understanding of the behavior of both nuclides in the ocean. Here an inverse method is used to evaluate the information contain...

Martin Plath1,2,3,4) (1 Unit of Animal Ecology, Department of Biochemistry and Biology, University of Potsdam, Maulbeerallee 1, 14469 Potsdam, Germany; 2 Unit of Evolutionary Biology and Systematic Zoology, Department of Biochemistry and Biology, University of Potsdam, Karl-Liebknecht-Str. 24-25, 14476 Potsdam, Germany; 3 Department of Zoology, University of Oklahoma, 730 Van Vleet Oval, Norman...

This paper presents an update semantic for dialogue acts, defined in terms of combinations of very simple ‘elementary update functions’. This approach allows fine-grained distinctions to be made between related types of dialogue acts, and relations like entailment and exclusion between dialogue acts to be established. The approach is applied to dialogue act representations as defined in the Dia...

This paper describes a method for automatically learning effective dialogue strategies, generated from a library of dialogue content, using reinforcement learning from user feedback. This library includes greetings, social dialogue, chit-chat, jokes and relationship building, as well as the more usual clarification and verification components of dialogue. We tested the method through a motivati...