• Publications
  • Influence
PARADISE: A Framework for Evaluating Spoken Dialogue Agents
TLDR
This paper presents PARADISE (PARAdigm for DIalogue System Evaluation), a general framework for evaluating spoken dialogue agents that decouples task requirements from an agent's dialogue behaviors, supports comparisons among dialogue strategies, and makes it possible to compare agents performing different tasks by normalizing for task complexity.
Towards developing general models of usability with PARADISE
TLDR
A number of models for predicting system usability (as measured by user satisfaction), based on the application of PARADISE to experimental data from three different spoken dialogue systems, are developed and shown to generalize well.
Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
TLDR
The design, construction and empirical evaluation of NJFun, an experimental spoken dialogue system that provides users with access to information about fun things to do in New Jersey, are reported on.
Empirical Studies on the Disambiguation of Cue Phrases
TLDR
This paper reports results of empirical studies on discourse and sentential uses of cue phrases, in which both text-based and prosodic features were examined for disambiguating power.
Spoken Versus Typed Human and Computer Dialogue Tutoring
TLDR
It is found that changing the modality from text to speech caused large differences in the learning gains, time and superficial dialogue characteristics of human tutoring, but for computer tutoring it made less difference.
Evaluating spoken dialogue agents with PARADISE: Two case studies
TLDR
PARADISE (PARAdigm for DIalogue System Evaluation), a general framework for evaluating and comparing the performance of spoken dialogue agents, is presented and can be used both for making predictions about future versions of an agent, and as feedback to the agent so that the agent can learn to optimize its behaviour based on its experiences with users over time.
A Plan Recognition Model for Subdialogues in Conversations
TLDR
This paper introduces a set of discourse plans, each one corresponding to a particular way that an utterance can relate to a discourse topic, and distinguish such plans from the set of plans that are actually used to model the topics.
Reinforcement Learning for Spoken Dialogue Systems
TLDR
A general software tool (RLDS, for Reinforcement Learning for Dialogue Systems) based on the MDP framework is built and applied to dialogue corpora gathered from two dialogue systems built at AT&T Labs, demonstrating that RLDS holds promise as a tool for "browsing" and understanding correlations in complex, temporally dependent dialogue Corpora.
Discourse Segmentation by Human and Automated Means
TLDR
The first part of this paper presents a method for empirically validating multitutterance units referred to as discourse segments, and reports highly significant results of segmentations performed by naive subjects, where a commonsense notion of speaker intention is the segmentation criterion.
...
...