Results 1 - 10 of 143,751

Annotating Conversations for Information State Updates

by Massimo Poesio, Robin Cooper, Staffan Larsson, Colin Matheson, David Traum , 1999
"... We present an experiment in annotating a dialogue using two different notions of information state: a stripped down variant of Ginzburg's view of the dialogue game board, including questions under discussion (QUD), and the dialogue model of Poesio and Traum which builds upon previous work by Tr ..."
Abstract - Cited by 8 (3 self) - Add to MetaCart
We present an experiment in annotating a dialogue using two different notions of information state: a stripped down variant of Ginzburg's view of the dialogue game board, including questions under discussion (QUD), and the dialogue model of Poesio and Traum which builds upon previous work

Dialogue Modeling as Information State Update

by Ivana Kruijff-korbayová, Ivana Kruijff-korbayová, Ivana Kruijff-korbayová, Ivana Kruijff-korbayová
"... • Representation of the current state of dialogue • Used by system to – Interpret user’s turn – Decide which external actions to take – Decide what to say – Store information (dialogue context representation) • Utterances update information state • Approaches to DM differ in how IS is represented, w ..."
Abstract - Add to MetaCart
• Representation of the current state of dialogue • Used by system to – Interpret user’s turn – Decide which external actions to take – Decide what to say – Store information (dialogue context representation) • Utterances update information state • Approaches to DM differ in how IS is represented

Imperfect Information State Updates by Utterances

by Tsutomu Fujinami , 1996
"... Introduction There are two complementary views on the meaning of sentences, static and dynamic. When one pays his attention to the static aspect, he is interested in what a sentence represents and how it could be interpreted against what model. When one is concerned with the dynamic aspect, on the ..."
Abstract - Add to MetaCart
, on the other hand, he becomes interested in how the representation can be changed by uttering the sentence. Models for such a state change have however not been investigated until recently. Among various theories applicable to the study of state changes, Channel Theory [Bar93, SB93] seems to be most promising

Information State Update: Semantics or Pragmatics?

by Raquel Fernández, Matthew Purver
"... We argue for an approach which treats the compositional semantic content of an utterance as including its basic dialogue update effects – those which can be derived entirely from its semantic and syntactic properties. This allows us to capture the distinction between these integral semantic contextu ..."
Abstract - Add to MetaCart
We argue for an approach which treats the compositional semantic content of an utterance as including its basic dialogue update effects – those which can be derived entirely from its semantic and syntactic properties. This allows us to capture the distinction between these integral semantic

DIPPER: Description and Formalisation of an Information-State Update Dialogue System Architecture

by Johan Bos, Ewan Klein, Oliver Lemon, Tetsushi Oka - In 4th SIGdial Workshop on Discourse and Dialogue , 2003
"... The DIPPER architecture is a collection of software agents for prototyping spoken dialogue systems. Implemented on top of the Open Agent Architecture (OAA), it comprises agents for speech input and output, dialogue management, and further supporting agents. We define a formal syntax and semantics fo ..."
Abstract - Cited by 73 (17 self) - Add to MetaCart
for the DIPPER information state update language. The language is independent...

Learning User Simulations for Information State Update Dialogue Systems

by Kallirroi Georgila, James Henderson, Oliver Lemon - in Eurospeech , 2005
"... This paper describes and compares two methods for simulating user behaviour in spoken dialogue systems. User simulations are important for automatic dialogue strategy learning and the evaluation of competing strategies. Our methods are designed for use with "Information State Update" (ISU) ..."
Abstract - Cited by 68 (21 self) - Add to MetaCart
This paper describes and compares two methods for simulating user behaviour in spoken dialogue systems. User simulations are important for automatic dialogue strategy learning and the evaluation of competing strategies. Our methods are designed for use with "Information State Update" (ISU

Combining Reinforcement Learning with Information-State Update Rules ∗

by unknown authors
"... Reinforcement learning gives a way to learn under what circumstances to perform which actions. However, this approach lacks a formal framework for specifying hand-crafted restrictions, for specifying the effects of the system actions, or for specifying the user simulation. The information state appr ..."
Abstract - Add to MetaCart
Reinforcement learning gives a way to learn under what circumstances to perform which actions. However, this approach lacks a formal framework for specifying hand-crafted restrictions, for specifying the effects of the system actions, or for specifying the user simulation. The information state

Combining Reinforcement Learning with Information-State Update Rules ∗

by unknown authors
"... Reinforcement learning gives a way to learn under what circumstances to perform which actions. However, this approach lacks a formal framework for specifying hand-crafted restrictions, for specifying the effects of the system actions, or for specifying the user simulation. The information state appr ..."
Abstract - Add to MetaCart
Reinforcement learning gives a way to learn under what circumstances to perform which actions. However, this approach lacks a formal framework for specifying hand-crafted restrictions, for specifying the effects of the system actions, or for specifying the user simulation. The information state

ADAPTIVE MULTIMODAL DIALOGUE MANAGEMENT BASED ON THE INFORMATION STATE UPDATE APPROACH

by unknown authors
"... This paper provides an overview of the aims of the TALK project 1 focusing on the issue of integrating Reinforcement Learning (RL) with the Information State Update (ISU) approach to dialogue management, in order to develop adaptive multimodal dialogue systems. The project will build showcases for i ..."
Abstract - Add to MetaCart
This paper provides an overview of the aims of the TALK project 1 focusing on the issue of integrating Reinforcement Learning (RL) with the Information State Update (ISU) approach to dialogue management, in order to develop adaptive multimodal dialogue systems. The project will build showcases

Incremental information state updates in an obligation-driven dialogue model

by Jörn Kreutel - Language and Computation , 2000
"... We sketch the outlines of a dialogue model using discourse obligations in a formal framework of information states. We propose a set of practical inference rules which incrementally update information states and assign intentional structures to sequences of dialogue moves. In this way we show that a ..."
Abstract - Cited by 9 (1 self) - Add to MetaCart
We sketch the outlines of a dialogue model using discourse obligations in a formal framework of information states. We propose a set of practical inference rules which incrementally update information states and assign intentional structures to sequences of dialogue moves. In this way we show
Results 1 - 10 of 143,751