Title: Selecting appropriate grammatical relations
for noun phrases in discourse
Author: Simon Corston-Oliver, simonco@microsoft.com
Topic Area: Pragmatic and/or Semantic modeling: focus and the distribution
of discourse referents
Key Words: grammatical relations, text generation, machine learning
Word Count: 3,194
Under consideration for other conferences (specify)? No
Full paper submission |
Abstract
We present a machine-learning approach to modeling the distribution
of noun phrases (NPs) within clauses with respect to a fine-grained taxonomy
of grammatical relations. We demonstrate that a cluster of superficial
linguistic features can function as a proxy for more abstract discourse
features that are not observable using state-of-the-art natural language
processing. The models constructed for actual texts can be used to select
among alternative linguistic expressions of the same propositional content
when generating discourse. |
|
Title: Issues in the transcription of English Conversational
Grunts
Author: Nigel Ward, nigel@sanpo.t.u-tokyo.ac.jp
Key Words: dialog annotation, backchannel feedback, filled pauses,
acknowledgements, phonetic properties
Word Count: 3100
Under consideration for other conferences (specify)? No
Full paper submission |
Abstract
Conversational grunts, such as uh-huh, un-hn, mm, and oh are ubiquitous
in spoken English, but no satisfactory scheme for transcribing these items
exits. This paper presents some facts about the phonetics of grunts,
proposes a transcription scheme, and evaluates its accuracy. |
|
Title: Dialogue Helpsystem based on Flexible Matching of User Query
with Natural Language Knowledge Base
Author: Sadao Kurohashi, kuro@i.kyoto-u.ac.jp
Topic Area: Dialogue, Context
Keywords: Dialogue system, Parsing, Knowledge base, Contextual Processing
Word Count: 3,180
Under Consideration for other Conferences (specify)? None
Full paper submission |
Abstract:
This paper describes a dialog helpsystem which advises users in using
computer facilities and software applications provided by the Center for
Information and Multimedia Studies, Kyoto University. The system
employs a knowledge base written in natural language and retrieves a proper
knowledge unit by flexible matching of user query with the knowledge base.
The system is running since July 1999, received about 2,000 queries so
far, and answered about 40\% of them satisfactory. |
|
Title: Dialogue and Domain Knowledge Management in
Dialogue Systems
Author: Annika Flycht-Eriksson and Arne Jönsson, annfl@ida.liu.se
Keywords: Dialogue management, domain knowledge management, dialogue
model, task model
Word Count: 2700
Under Consideration for other Conferences (specify)? No
Full paper submission |
Abstract:
Intelligent dialogue systems must be able to respond properly to a
variety of requests involving knowledge of the dialogue, the task at hand,
and the domain. We propose that it is important to understand the
nature of the various reasoning mechanisms involved and to separate not
only, interpretation, generation, and dialogue management but also domain
knowledge and task reasoning. In this paper we will focus on the
dialogue and domain knowledge reasoning components and show how they can
cooperate to achieve natural interaction. |
|
Title: Document Transformations and Information States
Author: Staffan Larsson and Annie Zaenen, sl@ling.gu.se
Keywords: information states, technical instructions, dialogue, genre
Word Count: 3200
Under Consideration for other Conferences (specify)? No
Full paper submission |
Abstract:
We discuss ways to explore how instructional material needs to be structured
to be presented with various degrees of interactivity. We use the
TRINDI information state approach to model three different degrees of interactivity
and present IMDiS, a small experimental implementation based on the the
GoDiS dialogue system. |
|
Title: Japanese Dialogue Corpus of Multi-Level Annotation
Author: Shu Nakazato, nakazato@mis.meiou.ac.jp
Keywords: multi-level annotation, dialogue corpus, prosody, dialogue
act, dialogue segment
Word Count: 2900
Which Session: General
Under consideration for other conferences (specify)? None |
Abstract:
This paper describes a Japanese dialogue corpus annotated with multi-level
information built by the Japanese Discourse Research Initiative, Japanese
Society of Artificial Intelligence. The annotation information consists
of speech, transcription delimited by slash units, prosodic, part or speech,
dialogue acts and dialogue segmentation. In the project, we used
the corpus for obtaining new findings by examining the relationship between
linguistic information and dialogue acts, that between prosodic information
and dialogue segment, and the characteristics of agreement/disagreement
expressions and non-sentence elements |
|
Title: Dialogue Management in the Agreement Negotiation
Process: A Model that Involves Natural Reasoning
Author: Mare Koit and H. Oim, koit@cs.ut.ee
Topic Area: Dialogue Systems
Key Words: dialogue management models, user and user group modelling
Which Session: General Session
Word Count: number of words, excluding title page and references -
3079
Under consideration for other conferences (specify)? No |
Abstract:
In the paper we describe an approach to dialogue management in the
agreement negotiation where one of the central roles is attributed to the
model of natural human reasoning. The reasoning model consists of the model
of human motivational sphere, and of reasoning algorithms. The reasoning
model is interacting with the model of communication process. The latter
is considered as rational activity where central role play the concepts
of communicative strategies and tactics. |
Title: Social Goals in Conversational Cooperation
Author: Guido Boella, Rossana Damiano and Leonardo Lesmo, rossana@di.unito.it
Keywords: Politeness, Dialogue Acts
Topic Area: Pragmatic and Semantic modeling
Which Session: general
Word Count: 3200
Under consideration for other conferences: none |
Abstract:
We propose a model where dialog obligations arise from the interplay
of social goals and intentions of the participants: when an agent is addressed
with a request, the agent's decision to commit to the requester's linguistic
and domain goals is motivated by a trade-off between the preference for
preventing a negative reaction of the partner and the cost of actions needed
to satisfy the goals. |
Title: Abstract Anaphora Resolution in Danish
Author: Costanza Navarretta, costanza@cst.ku.dk
Topic Area: pragmatics and/or semantic modeling
Keywords: anaphora resolution, discourse deictics, dialogues
Which Session: General
Word Count: 3113
Under consideration for other conferences (specify)? None |
Abstract:
In this paper we present an adaptation to Danish discourse of the
Eckert and Strube's algorithm for resolving
anaphora referring to individual NPs and abstract objects in English
dialogues [Eckert and Strube, 1999b; Eckert and Strube, 1999a]. The adapted
algorithm is tested on two kinds of dialogues and the results obtained
are evaluated. |
Title: Flexible Speech Act Based Dialogue Management
Author: Eli Hagen, hagen@cs.sfu.ca
Keywords: dialogue managment models, mixed initiative and useradaptive
dialogue, dialouge acts,
Session: General
Under consideration for other conf.: No |
Abstract:
We present an application independent dialogue engine that reasons
on application dependent resources to calculate predictions about how a
dialogue might continue. Predictions are language independent and are translated
into language dependent structures for recognition and synthesis. Further,
we discuss how the predictions account for different kinds of dialogue,
e.g., questionanswer or mixed initiative. |
Title: Identifying prosodic indicators of dialogue
structure: some methodological and theoretical considerations.
Author: Ilana Mushin, Lesley Stirling, Janet Fletcher, Roger Wales,
i.mushin@linguistics.unimelb.edu.au
Topic Area: prosody and discourse
Key Words: dialogue, prosody, grounding, annotation
Which Session: general session (G) for workshop
Word Count: 2752
Under consideration for other conferences (specify)? no |
Abstract:
This paper presents an empirical analysis of prosodic phenomena (intonation
and timing) in ?common ground units? (Nakatani & Traum 1999) to show
to address questions of the role of prosody in dialogue while taking into
account the complexities of multispeaker discourse. This paper addresses
the methodological concerns of how best to carry out a study of this kind
as well as our key theoretical questions about prosody and discourse structure. |
Title: ADAM: An Architecture for xml-based Dialogue
Annotation on Multiple levels
Authors: Claudia Soria (ILC-CNR, Pisa, Italy - soria@ilc.pi.cnr.it),
Roldano Cattoni, Morena Danieli
Key Words: spoken Italian dialogue corpus, XML-based dialogue annotation,
multi-level annotation.
Which Session: General
Word Count: 3153
Under consideration for other conferences ? No |
Abstract:
In this paper annotation modularity and use of annotation meta-schemes
are identified as basic requirements for achieving actual corpora reusability.
We discuss these concepts and the way they are implemented in the architectural
framework of the ADAM corpus, which is a corpus of 450 Italian spontaneous
dialogues. The design of ADAM architecture is compatible with as many practices
of dialogue annotation as possible, as well as approaches to annotation
at different levels. |
|
Title: Some Notes on the Complexity of Dialogues
Authors: Jan Alexandersson, Paul Heisterkamp, alexandersson@dfki.de
Topic Areas: Dialogue Evaluation
Keywords: Dialogue complexity. Common tools and infrastructures
for evaluation
Which Session? theme session on principles for evaluation of dialogue
systems
Word Count: 2983
Under consideration for other conferences? None |
Abstract:
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 impoissible to test even
a percentage of the theoretically possible utterances in a reasonbable
amount of time. An even smaller part of possible dialogues can thus
be tested. Second, an approach for early testing of the dialogue
manager of a dialogue system, without the complete system being put together
is described. |
|
Title: Using Coreferences for Coherence Relations +Adjuncts as Discourse Units ---An Empirical
Examination of Coherence Relations
Authors: Holger Schauer, Udo Hahn, Holger.Schauer@gmx.de
Topic Areas: Pragmatics, Discourse Structure
Keywords: discourse, text coherence, computational semantics
Which Session? G
Word Count: 3193
Under consideration for other conferences? CogSci2000,ACL2000 Student Workshop |
Abstract:
The automated derivation of the discourse structure of a given text has currently concentrated on the use
of explicit linguistic cues. We will argue that referential expressions also considerably contribute to a
text's structure. We argue that any analysis of discourse structure should obey the referential
dependencies in a text. Under this assumption, the resolution of anaphoric expressions can be used as a
guideline for the automated derivation of the discourse structure of a text. Finally, the proposed
algorithm is evaluated.
Coherence relations have mainly been studied as a mechanism for the
representation of text structure based on the analysis of clauses and larger
text units. A closer look at discourse data reveals, however, that
adjuncts, typically cued by prepositions, also have a coherence establishing
function. We discuss empirical evidence for this claim, and outline
a framework that integrates the semantic interpretaion and recognition
of coherence relations covert in prepositional phrases. |
|
Title: The MATE Markup Framework
Authors: Laila Dybkjær, Niels Ole Bernsen, nob@nis.sdu.dk
Keywords: markup framework, coding module, spoken dialogue corpora,
multilevel annotation, usability.
Session: General.
Word count: 3199
Under consideration for other conferences: No. |
Abstract:
For two years, the European Telematics project MATE has worked towards
facilitating re-use of annotated spoken language data, addressing theoretical
issues and implementing practical solutions which could serve as standards
in the field. The resulting MATE Workbench for corpus annotation is now
available as licensed open source software. This paper describes the MATE
markup framework which is proposed as a standard for the definition and
representation of markup for spoken dialogue corpora, and presents early
experience from use of the framework. |
|
Title: WIT: A Toolkit for Building Robust and Real-Time
Spoken Dialogue Systems
Authors: Mikio Nakano, Noboru Miyazaki, Norihito Yasuda, Akira Sugiyama,
Jun-ichi Hirasawa, Kohji Dohsaka, Kiyoaki Aikawa, nakano@sls.lcs.mit.edu
Topic Area(s): Dialogue Systems
Keywords: Spoken dialogue system, Toolkit, Task-portability, Robustness,
Real-time response
Which Session: T1, T2, T3, T4, or G (you must choose only one)? General
Word Count: 3,165
Under consideration for other conferences (specify)? None |
Abstract:
This paper describes WIT, a toolkit for building spoken dialogue systems.
WIT features an incremental understanding mechanism that enables robust
utterance understanding and real-time responses. WIT's ability to compile
domain-dependent system speci cations into internal knowledge sources makes
building spoken dialogue systems much easier than it is from scratch. |
|
Title: A Common Theory of Information Fusion from
Multiple Text SourcesStep One: Cross-document Rhetorical Structure
Author: Drago Radev, radev@umich.edu
Key Words: rhetorical structure, temporal structure, cross-document
structure theory, multidocument summarization, evolving documents
Which Session: general
Word Count: 3,198 exclusive of title page and references
Under consideration for other conferences (specify)? NO |
Abstract:
We introduce CST (cross-document structure theory), a paradigm for
multi-document analysis. CST takes into account the rhetorical structure
of clusters of related textual documents. We present a taxonomy of cross-documentrelationships.
We argue that CST can be the basis for multi-document summarization guided
by user preferences for summary length, information provenance, cross-source
agreement, and chronological ordering of facts. |
|
Title: Dynamic user level and utility measurement
for adaptive dialog in a help-desk system.
Authors: Preetam Maloor, Joyce Chai, Jchai@us.ibm.com
Keywords: Dialog System, Adaptive Dialog Strategies, User Modeling,
Utility Measurement
Subject Area: Dialog Systems, user and user group modeling, mixed initiative
and user-adaptive dialogue
Which Session: General Session (short paper submission)
Word Count: 1952
Under consideration for other conferences: none |
Abstract:
The learning and self-adaptive capability in natural dialog systems
has become increasingly important with the advance in wide applications
of dialog systems. For any application, particularly, one dealing with
a technical domain, not only the system should pay attention to the user
experience level and dialog goals, but more importantly, the mechanism
to adapt the system behavior to the evolving state of the user and the
world. This paper describes a proposed methodology that automatically identifies
and updates user experience level and sub-goal utilities to direct adaptive
dialog strategies and management. |
|
