Trainable sentence planning for complex information presentation in spoken dialog systems
Published 1 January 2004
Amanda Stent, Rashmi Prasad, Marilyn Walker
Citations153
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
It is shown that trainable sentence planning can produce output comparable to that of MATCH's template-based generator even for quite complex information presentations.
Abstract
A challenging problem for spoken dialog systems is the design of utterance generation modules that are fast, flexible and general, yet produce high quality output in particular domains. A promising approach is trainable generation, which uses general-purpose linguistic knowledge automatically adapted to the application domain. This paper presents a trainable sentence planner for the MATCH dialog system. We show that trainable sentence planning can produce output comparable to that of MATCH's template-based generator even for quite complex information presentations.
Keywords
Computer Science
A brief introduction to boosting
1,208 Citations1999Robert E. Schapire
The boosting algorithm AdaBoost is introduced, and the underlying theory of boosting is explained, including an explanation of why boosting often does not suffer from overfitting.
A centering approach to pronouns
540 Citations1987Susan E. Brennan, Marilyn Walker Friedman +1 more
A formalization of the centering approach to modeling attentional structure in discourse is presented and used as the basis for an algorithm to track discourse context and bind pronouns and proposes an extension to these states of continuing, retaining and shifting.
IPrA Papers in PragmaticsRhetorical structure theory
267 Citations2015Sandra A. Thompson, William C. Mann
Rhetorical Structure Theory is a theory of text organization which provides a framework for an analysis of text, and its mechanisms and applications include studies of clause combining, coherence and assertional effects of discourse structure.
MATCH
220 Citations2001Michael Johnston, Srinivas Bangalore +6 more
This work describes a multimodal application architecture which combines finite-state multimodAL language processing, a speech-act based multimodals dialogue manager, dynamic multimodale output generation, and user-tailored text planning to enable rapid prototyping of multimodality interfaces with flexible input and adaptive output.
A fast and portable realizer for text generation systems
203 Citations1997Benoit Lavoie, Owen Rambow
A mixer block used in rotary drums to improve the efficiency of mixing, drying, cooling, heating, or calcining of solid materials such as gravel, stone, fluxes and the like to produce a more uniform product with minimal production of fines and dust is described.
Forest-based statistical sentence generation
147 Citations2000Irene Langkilde
A new approach to statistical sentence generation is presented in which alternative phrases are represented as packed sets of trees, or forests, and then ranked statistically to choose the best one, and an efficient ranking algorithm is described.
Computer Speech & LanguageTraining a sentence planner for spoken dialogue using boosting
92 Citations2002Marilyn Walker, Owen Rambow +1 more
SPoT, a trainable sentence planner, and a new methodology for automatically training SPoT on the basis of feedback provided by human judges, which shows that SPiT performs better than the rule-based systems and the baselines, and as well as the hand-crafted system.
Edinburgh Research Explorer (University of Edinburgh)Beyond Elaboration: The Interaction of Relations and Focus in Coherent Text
90 Citations2000Alistair Knott, Jon Oberlander +2 more
Edinburgh Research Explorer (University of Edinburgh)Experiments Using Stochastic Search for Text Planning
75 Citations1998Chris Mellish, Alistair Knott +2 more
This work takes as its starting point Marcu's excellent formalisation of R S T and the problem of building legal RST trees, and for the purposes of this paper the phrase "text planning" will generally denote the task characterised by him.
Applied text generation
73 Citations1992Owen Rambow, Tanya Korelsky
This paper will present the system and show how these design objectives led to particular design decisions, and address the problem of portability.
From local to global coherence: a bottom-up approach to text planning
54 Citations1997Daniel Marcu
A new, data-driven approach to text planning is presented, which can be used not only to map full knowledge pools into natural language texts, but also to generate texts that satisfy multiple, high-level communicative goals.
Edinburgh Research Explorer (University of Edinburgh)Speech-Plans: Generating Evaluative Responses in Spoken Dialogue
26 Citations2002Marilyn Walker, Steve Whittaker +5 more
This work builds on previous work using multiattribute decision theory to devise speech-planning algorithms that present usertailored summaries, comparisons and recommendations that allow users to focus on critical differences between options and their attributes.
Evaluating a trainable sentence planner for a spoken dialogue system
22 Citations2001Owen Rambow, Monica Rogati +1 more
It is shown that the trainable sentence planner performs better than the rule-based systems and the baselines, and as well as the hand-crafted system.