This paper concerns dialogue management for spoken dialogue. We show why we do not use speech-act related units or intentions. We base our approach on belief states of the system. Layered units are used to construct a pragmatic interpretation of these states and to determine the dialogue continuation as a local optimisation over a set of dynamic dialogue goals. We point to systems that successfully employ this approach.

This paper revisits word lattice search whose task is to find a plausible semantic interpretation for a given utterance. Our approach of interleaved search and analysis is designed to break the frontier of "toy" applications. The framework is implemented in two interacting modules, running in parallel. Instead of simply parsing a word lattice, we rather do tree decoding with a probabilistic approximation of a given grammar, employing a beam search strategy. Logical form is build up in tandem according to the decoded derivation histories, using a codescriptive HPSG grammar for dialog turns. The proposed architecture only uses the knowledge necessary in every processing step, the key aspect being an asynchronous coupling of the two specialized modules.

We present two concepts for systems with language identification in the context of multilingual information retrieval dialogs. The first one has an explicit module for language identification. It is based on training a common codebook for all the languages and integrating over the output probabilities of language specific n--gram models trained over the codebook sequences. The system can decide for one language either after a predefined time interval or if the difference between the probabilities of the languages succeeds a certain threshold. This approach allows to recognize languages that the system can not process and give out a prerecorded message in that language. In the second approach, the trained recognizers of the languages to be recognized, the lexicons, and the language models are combined to one multilingual recognizer. Only allowing transitions between the words from one language, each hypothesized word chain only contains words from one language and language identification is an implicit by-product of the speech recognizer. First results for both language identification approaches are presented.

The purpose of this paper is twofold. First, we describe some complexity aspects of spoken dialogue. It is shown that, given the internal setting of our dialogue system, it is impossible to test even a small percentage of the theoretically possible utterances in a reasonable amount of time. An even smaller part of possible dialogues can thus be tested. Secondly, an approach for early testing of the dialogue manager of a dialogue system, without the complete system being put together, is described.

Abstract not found