Stochastic language generation for spoken dialogue systems
Published 1 January 2000Open access
Alice Oh, Alexander I. Rudnicky
Citations156
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper proposes a new corpus-based approach to natural language generation, specifically designed for spoken dialogue systems, that is based on template-based and rule-based NLG approaches.
Abstract
The two current approaches to language generation, template-based and rule-based (linguistic) NLG, have limitations when applied to spoken dialogue systems, in part because they were developed for text generation. In this paper, we propose a new corpus-based approach to natural language generation, specifically designed for spoken dialogue systems.
Keywords
Computer Science
Journal of the American Statistical AssociationStatistical Methods for Speech Recognition
1,988 Citations1999Don X. Sun, Frederick Jelinek
The speech recognition problem hidden Markov models the acoustic model basic language modelling the Viterbi search hypothesis search on a tree and the fast match elements of information theory.
Statistical language modeling using the CMU-cambridge toolkit
564 Citations1997Philip Clarkson, Roni Rosenfeld
The conventional language modeling technology, as implemented in the toolkit, is outlined, and the extra e(cid:14)ciency and functionality that the new toolkit provides as compared to previous software for this task is described.
International Journal of Man-Machine StudiesSteps toward graceful interaction in spoken and written man-machine communication
103 Citations1983Philip J. Hayes, D. Raj Reddy
This paper proposes a decomposition of graceful interaction into a number of relatively independent skills: skills involved in parsing elliptical, fragmented, and otherwise ungrammatical input; in ensuring robust communication; in explaining abilities and limitations, actions and the motives behind them; in keeping track of the focus of attention of a dialogue.
Using argumentation to control lexical choice: a functional unification implementation
96 Citations1993Michael Elhadad
New surface generation techniques that improve on both aspects of surface generation are presented, which allow a purely conceptual input to be expressed by a greater variety of linguistic forms and with more sensitivity to pragmatic factors than was previously possible.
ArXiv.orgA Flexible Shallow Approach to Text Generation
67 Citations1998Stephan Busemann, Helmut Horacek
Data collection and analysis in the air travel planning domain
30 Citations1989Jacqueline Kowtko, Patti Price
This work has collected, transcribed and analyzed over 8 hours of human-human interactive problem solving dialogue in the air travel planning domain, including traveler-agent dialogues and the more constrained agent-airline dialogues, to define and test an initial vocabulary, and to design an appropriate interface.
Client / world model synchronous alignement for speaker verification
30 Citations1999Johnny Mariéthoz, Dominique Genoud +2 more
Do the right thing . . . but expect the unexpected
17 Citations1998Jon Oberlander
Content planning and generation in continuous-speech spoken dialog systems∗
13 Citations2000Amanda Stent
An architecture for generation is proposed that combines grammar-based and templates, capitalizing on their strengths and minimizing their weaknesses, to answer the question, “How far can templates take us?”
Data Collection and Analysis in the Air Travel Planning Domain
7 Citations1989Jacqueline Kowtko, Patti Price