Abstract:
We explore the notion of information state in relation to dialogue
systems, and in particular to the part of a dialogue system we call
the dialogue move engine. We use a framework for experimenting with
information states and dialogue move engines, and show how an
experimental dialogue system currently being developed in Göteborg
within the framework can be provided with rules to handle
accommodation of questions and plans in dialogue.
Full Version:
Postscript, ,
HTML
Date of Submission: October 11, 1999
Last Comments: February 3, 2000
Please click here to access the paper's discussion page.
Abstract:
We describe an implemented spoken-language dialogue system for a
travel-planning domain, which accesses a commercially available
travel-information web-server and supports a flexible mixed-initiative
dialogue strategy. We argue, based on data from initial Wizard-of-Oz
experiments, that mixed-initiative strategies are appropriate for many
types of user, but require more sophisticated architectures for
processing of language and dialogue; we then use these observations to
motivate an architecture which combines parallel deep and shallow
natural language analysis engines and an agenda-driven dialogue
manager. We outline the top-level processing strategy used by the
dialogue manager, and also a novel formalism, which we call Flat
Utterance Description, that allows us to reduce the output of the deep
and shallow language-processing engines to a common representation.
Full Version:
Postscript,
,HTML
Date of Submission: October 25, 1999
Last Comments: None so far
Please click here to access the paper's discussion page.
Abstract:
We show how the specification of a dialogue system can be divided into
domain-dependent and domain-independent parts. We demonstrate how
comparisons of actual representations in the dialogue history can help
to infer hierarchical dialogue structure. The principles guiding the
inference can be expressed in domain independent rules. Using typed
feature structures as the only representation formalism for
domain-dependent knowledge we retain the simplicity of frame-based
systems in terms of gathering necessary information to fulfil a
task. On the other hand, being able to easily integrate a type
hierarchy into the representations and describing the systems behavior
in clauses quantifying over feature structures in the dialogue
history, we not only achieve a compact specification of the system's
behavior, but also a type discipline that helps to detect errors in
specification before system deployment. The described implementation
is a first step towards the implementation of domain-independent
task-oriented dialogue processing systems.
Full Version:
Postscript,
HTML
Date of Submission: October 26, 1999
Last Comments: None so far
Please click here to access the paper's discussion page.
Abstract:
Dialogue systems utilise a variety of knowledge sources and
models. However, there is a confusion concerning the purposes and
contributions of specific models and the relationships among them. In
this paper we present a study of different dialogue systems and the
knowledge sources and models they use. The models are characterised in
terms of what knowledge they contain and the roles of various models
and the relations between them are discussed. Implications for
development of dialogue systems are also presented.
Full Version:
Postscript,
HTML
Date of Submission: October 26, 1999
Last Comments: None so far
Please click here to access the paper's discussion page.
Abstract:
In this paper we present the task-oriented context representation and the
dialogue manager for the {\sc Verbmobil} translation system. We show how to
utilize statistical methods, shallow extraction and propositional
representation to provide translation relevant information and most of all, to
enable the system to automatically create a dialogue script and result summary.
Full Version:
Postscript,
HTML
Date of Submission: October 26, 1999
Last Comments: None so far
Please click here to access the paper's discussion page.
Abstract:
Spoken Language Dialogue Systems which allow for spontaneous speech are not
very widely spread. You find a few systems in application domains such as train
time-table information or flight ticket reservation (see Bernsen et al. (1998) for
an overview). One reason for the lack of good interactive dialogue systems is
their complexity. To develop a system which is able to handle more than simple
commands and phrases requires a lot of experience and time. For every
application domain different kinds of knowledge bases have to be specified. To
be able to accelerate this process and to make it also transparent for
non-experts we are currently working on methods and tools which support this
development. Our aim is to provide specification models which are universal
enough to be interpreted within different dialogue systems, i.e. different
implementations of generic conversational systems. With the help of
special design methods and a uniform representation of data the tools will
allow a consistent specification of dialogue systems and a transformation
between different models.
Full Version:
Postscript,
HTML
Date of Submission: October 26, 1999
Last Comments: None so far
Please click here to access the paper's discussion page.
Abstract:
We consider the requirements of an ideal automated argumentation system
designed to model human interactions and compare them with the
capabilities of our argumentation system, NAG. We ground our discussion
with a description of NAG's architecture, particularly emphasizing NAG's
knowledge representation scheme, which supports the consideration of
domain and user model information as well as contextual information when
reasoning about arguments.
Full Version:
Postscript
Date of Submission: October 28, 1999
Last Comments: February 7, 2000
Please click here to access the paper's discussion page.
Abstract: The general goal of our work is to investigate
computational models of dialog that can support effective interaction
between people and computer systems. We are particularly interested in
the use of dialog for training and education. To support effective
communication, dialog systems must facilitate users' understanding by
incrementally presenting only the most relevant information, by
evaluating users' understanding, and by adapting the interaction to
address communication problems as they arise.
Our theory provides a specification and representation of
the linguistic, intentional, and social information that influence how
people understand and respond in an ongoing dialog and an architecture
for combining this information. We represent knowledge
uniformly in a single, declarative, logical language where the
interpretation and performance of communicative acts in dialog occurs
as a result of reasoning.
Full Version:
PDF, ,
HTML
Date of Submission: October 28, 1999
Last Comments: None so far
Please click here to access the paper's discussion page.
Abstract:
In the processing of spontaneous language, information concerning
discourse-level co-occurrences of words or morphemes - relatively long-term
predictions on the scale of several utterances - may help to reduce perplexity
in speech recognition, facilitate lexical disambiguation, and contribute to
topic tracking. This working paper describes a new set of facilities for
tracking lexical co-occurrences. The major innovation is the use of semantic
smoothing: we track co-occurrences of semantic tokens associated with words or
morphs in addition to co-occurrences of the words or morphs themselves. Such
smoothing offers an approach to the problem of data sparseness: it is possible
to retrieve reasonable semantically-mediated associations for morphs not in the
training corpus. We report on preliminary experiments with a corpus of
morphologically-tagged transcripts of 16 spontaneous Japanese dialogues
concerning direction-finding and hotel arrangements. We close with discussion
of lexical disambiguation and topic tracking as they relate to co-occurrence
networks.
Full Version:
Postscript, , HTML
Date of Submission: October 30, 1999
Last Comments: None so far
Please click here to access the paper's discussion page.
Abstract: We propose a representation of local dialogue context
motivated by the need to react appropriately to meta-dialogue, such as
various sorts of corrections to the sequence of an instruction and
response action. Such context includes at least the following aspects:
the words and linguistic structures uttered, the domain correlates of
those linguistics structures, and plans and actions in response. Each
of these is needed as part of the context in order to be able to
correctly interpret the range of corrections. Partitioning knowledge
of dialogue structure in this way may lead to an ability to represent
generic dialogue structure (e.g., in the form of axioms), which can be
particularized to the domain, topic and content of the dialogue.
Full Version:
Postscript
Date of Submission: October 30, 1999
Last Comments: None so far
Please click here to access the paper's discussion page.