Discourse segmentation of spoken dialogue: an empirical approach
DSpace@MIT (Massachusetts Institute of Technology)Published 1 January 1998Open access
Giovanni Flammia, Victor W. Zue
Citations25
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
The analysis of an annotated corpus of information-seeking dialogues provides substantial empirical evidence about the di erences between human-to-human conversation and current interactive voice response systems (IVRs) and question-answer systems (QAs).
Abstract
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1998.
Keywords
Computer Science
LanguageA simplest systematics for the organization of turn-taking for conversation
11,020 Citations1974Harvey Sacks, Emanuel A. Schegloff +1 more
On the basis of research using audio recordings of naturally occurring conversations, the chapter highlights the organization of turn taking for conversation and extracts some of the interest that organization has.
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
Speech Acts: An Essay in the Philosophy of Language
6,641 Citations1969John R. Searle
SemioticaOpening up Closings
4,230 Citations1973Emanuel A. Schegloff, Harvey Sacks
Some of the ways that have been developed for dealing with closings in conversation are presented and an attempt to specify the domain for which the closing problems, as they have been posed, seem apposite is closed.
CognitionReferring as a collaborative process
2,412 Citations1986Herbert H. Clark, Deanna Wilkes-Gibbs
A communication task in which pairs of people conversed about arranging complex figures is described and how the proposed model accounts for many features of the references they produced is shown.
Journal of Educational StatisticsObserving Interaction: An Introduction to Sequential Analysis
2,312 Citations1988Victor L. Willson, Roger Bakeman +1 more
Cognitive ScienceContributing to Discourse
1,549 Citations1989Herbert H. Clark, Edward F. Schaefer
A model of contributions is described as parts of collective acts performed by the participants working together and it is shown how it accounts for o variety of features of everyday conversations.
TextTiling: segmenting text into multi-paragraph subtopic passages
1,253 Citations1997Marti A. Hearst
The algorithm is fully implemented and is shown to produce segmentation that corresponds well to human judgments of the subtopic boundaries of 12 texts, which should be useful for many text analysis tasks, including information retrieval and summarization.
Modern Language JournalTowards an analysis of discourse
1,112 Citations1977John McH. Sinclair, Malcolm Coulthard
Language and SpeechThe Hcrc Map Task Corpus
1,010 Citations1991Anne H. Anderson, Miles Bader +11 more
A corpus of unscripted, task-oriented dialogues which has been designed, digitally recorded, and transcribed to support the study of spontaneous speech on many levels is described.
Artificial IntelligenceCollaborative plans for complex group action
970 Citations1996Barbara J. Grosz, Sarit Kraus
A revised and expanded version of SharedPlans that reformulates Pollack's (1990) definition of individual plans to handle cases in which a single agent has only partial knowledge and has the features required by Bratman's (1992) account of shared cooperative activity.
Lexical cohesion computed by thesaural relations as an indicator of the structure of text
941 Citations1991Jane Morris, Graeme Hirst
IEEE Transactions on Acoustics Speech and Signal ProcessingSpeaker-independent phone recognition using hidden Markov models
936 Citations1989K.-F. Lee, Hsiao-Wuen Hon
The authors introduce the co-occurrence smoothing algorithm, which enables accurate recognition even with very limited training data, and can be used as benchmarks to evaluate future systems.
Columbia Academic Commons (Columbia University)The Meaning of Intonational Contours in the Interpretation of Discourse
833 Citations1990Janet B. Pierrehumbert, Julia Hirschberg
This paper proposes that a speaker chooses a particular tune to convey a particular relationship between an utterance, currently perceived beliefs of a hearer or hearers, and anticipated contributions of subsequent utterances, and claims that these relationships are compositionalcomposed from the pitch aumts, phrase QCcmts, and bowndary tones that make up tunes.
Language<b>The syntactic phenomena of English</b> . 2nd edn. By James D. McCawley. Chicago: University of Chicago Press, 1998. Pp. xxiv, 809. Cloth $110, paper $50.
781 Citations2000Andrew Rosta
New to this edition are sections on appositive constructions, parasitic gaps, contrastive negation, and comparative conditional sentences, as well as expanded coverage of cleft sentences and free relatives.
The MIT Press eBooksPlans for Discourse
486 Citations1990Barbara J. Grosz, Candace L. Sidner
A model of the collaborative plans of agents achieving joint goals is proposed and the role of these plans in discourses is illustrated.
Computational LinguisticsThe reliability of a dialogue structure coding scheme
401 Citations1997Jean Carletta, Stephen Isard +4 more
This paper describes the reliability of a dialogue structure coding scheme based on utterance function, game structure, and higher-level transaction structure that has been applied to a corpus of spontaneous task-oriented spoken dialogues.
Artificial IntelligenceAutomated discourse generation using discourse structure relations
308 Citations1993Eduard Hovy
Several facets of discourse structure relations as they are required by and used in text planners are outlined—their nature, number, and extension to associated tasks such as sentence planning and text formatting.
From discourse structures to text summaries
268 Citations1997Daniel Marcu
The rhetorical parsing, summarization, and generation of natural language texts
243 Citations1998Graeme Hirst, Daniel Marcu
This thesis is an inquiry into the nature of the high-level, rhetorical structure of unrestricted natural language texts, computational means to enable its derivation, and two applications (in automatic summarization and natural language generation) that follow from the ability to build such structures automatically.
Computational IntelligenceCONVERSATION ACTS IN TASK‐ORIENTED SPOKEN DIALOGUE
227 Citations1992David Traum, Elizabeth Hinkelman
Conversation acts, it will be seen, better account for the success of conversation than speech act theory alone and provide a pragmatic view of meaning in which the literal/non‐literal distinction is simply irrelevant.
Computational LinguisticsDiscourse segmentation by human and automated means
215 Citations1997Rebecca J. Passonneau, Diane Litman
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.
A prosodic analysis of discourse segments in direction-giving monologues
191 Citations1996Julia Hirschberg, Christine H. Nakatani
The effects of speaking style and of discourse segmentation method (text-alone versus text-and-speech) on the nature of this relationship between intonational variation and discourse structure are examined.
Speech CommunicationManaging problems in speaking
190 Citations1994Herbert H. Clark
There is evidence that the participants have joint strategies for preventing, warning about and repairing problems at each of these levels, and that they prefer preventatives to warnings, and warnings to repairs, all other things being equal.
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)Focusing and Description in Natural Language Dialogues
170 Citations1979Barbara J. Grosz
The relationship between focusing and definite descriptions in dialogue and its implications for natural language processing systems is examined and future research problems entailed in modeling the focusing process more generally are indicated.
The rhetorical parsing of natural language texts
151 Citations1997Daniel Marcu
Knowledge-Based SystemsInteraction and feedback in a spoken language system: a theoretical framework
149 Citations1995Susan E. Brennan, Eric A. Hulteen
Submitted to the AAAI-93 Fall Symposium on Human-Computer Collaboration: Reconciling theory, synthesizing practice.
SciDok (Saarland University and State Library)Dialogue acts in VERBMOBIL
140 Citations1995Susanne Johanna Jekat, Alexandra Klein +4 more
Automatic detection of discourse structure for speech recognition and understanding
124 Citations2002Daniel Jurafsky, Rebecca Bates +8 more
A new approach for statistical modeling and detection of discourse structure for natural conversational speech, based on 42 dialog acts, which achieves a 65% dialog act detection rate based on acoustic waveforms, and 72% accuracy based on word transcripts.
Lecture notes in computer scienceProsody in Speech Understanding Systems
117 Citations1997Ralf Kompe
The baseline ASU systems, including prosodic labeling and speech corpora, and prosodic phrase models, suggest that prosodic attributes in ASU are likely to be related to language quality.
Morgan Kaufmann Publishers Inc. eBooksUser Interface Management Systems: Models and Algorithms
94 Citations1992Dan R. Olsen
All major approaches to User Interface Management Systems development from a programmer's algorithmic perspective are brought together for the first time.
Elsevier eBooksUnderstanding Spoken Language
89 Citations1981Donald E. Walker
Fahlman's restriction that "No clause may be part of the specification of more than one *EVERYnode" can be seen as eliminating the possibility of representing statements of the form (Ax)(Ay) {S(x,y) > I(x-y)}.
Speech CommunicationRepairing conversational misunderstandings and non-understandings
89 Citations1994Graeme Hirst, Susan McRoy +3 more
A model that combines intentional and social accounts of discourse to support the negotiation of meaning is developed, which extends intentional accounts by using expectations deriving from social conventions in order to guide interpretation.
Discourse Structure in Spoken Language: Studies on Speech Corpora
89 Citations1995Christine H. Nakatani, Julia Hirschberg +1 more
Results of pilot studies that demonstrate reliable correlations of discourse and speech properties are summarized, and findings on a new corpus of direction-giving monologues, collected in both spontaneous and read speaking styles are reported.
arXiv (Cornell University)Manual Annotation of Translational Equivalence: The Blinker Project
86 Citations1998I. Dan Melamed
The annotated texts, the specially-designed annotation tool, and the strategies employed to increase the consistency of the annotations are described, which indicate that the Annotations are reasonably reliable and that the method is easy to replicate.
arXiv (Cornell University)Limited attention and discourse structure
73 Citations1996Marilyn Walker
The role de l'attention limitee dans un modele informatique de traitement du discours is examiner d'un modele de cache propose comme une implementation informatiques de la memoire de travail humaine.
Using collaborative plans to model the intentional structure of discourse
72 Citations1995Karen E. Lochbaum
A computational model for recognizing intentional structure and utilizing it in discourse processing is provided that satisfies the requirements of Grosz and Sidner's (1986) theory of discourse structure and also simplifies and extends previous plan-based approaches to dialogue understanding.
arXiv (Cornell University)Automating Coreference: The Role of Annotated Training Data
69 Citations1998Lynette Hirschman, Patricia Robinson +2 more
A study of interannotator agreement in the coreference task as defined by the Message Understanding Conference (MUC-6 and MUC-7) clarified and simplified the annotation specification, and an analysis of disagreement among several annotators concluded that only 16% of disagreements represented genuine disagreement about coreference.
Speech CommunicationFirst steps towards statistical modeling of dialogue to predict the speech act type of the next utterance
69 Citations1994Masaaki Nagata, Tsuyoshi Morimoto
It is shown that the dialogue model can predict the speech act type of the next utterance by experiments on 100 keyboard dialogues, and that it can make a better language model by combining the Dialogue model with a sentence model.
The TRAINS Project
66 Citations1991James F. Allen, Lenhart K. Schubert
The TRAINS project serves as an umbrella for research that involves pushing the state of the art in real-time planning, planning in uncertain worlds, plan monitoring and execution, natural language understanding techniques applicable to spoken language, and natural language dialog and discourse modelling.
Speech CommunicationProsodic and lexical indications of discourse structure in human-machine interactions
65 Citations1997Marc Swerts, Mari Ostendorf
The study reveals that in human-machine interactions, both discourse segmentation and utterance purpose can have particular prosodic correlates, although speakers also mark this information through choice of wording.
Computer Speech & LanguageDiscourse structure and performance efficiency in interactive and non-interactive spoken modalities
65 Citations1991Sharon Oviatt, Philip R. Cohen
Two speech modalities that represent opposites on the spectrum of speaker interaction—the telephone dialogue and audiotape monologue are examined, providing a comprehensive analysis of basic differences in discourse organization, referential characteristics and performance efficiency.
Digital Access to Scholarship at Harvard (DASH) (Harvard University)Instructions for annotating discourse
55 Citations1995Christine H. Nakatani, Barbara J. Grosz +2 more
This guide contains instructions for segmenting discourse that are meant to be self-contained and can be used by "naive" subjects, i.e., segmenters who have not studied discourse theory or discourse processing methods.
Discourse ProcessesCooperativity in human‐machine and human‐human spoken dialogue
55 Citations1996Niels Ole Bernsen, Hans Dybkjær +1 more
Concepts of dialogue cooperativity derived from a corpus of task‐oriented spoken human‐machine dialogue provided an empirical test of the correctness and completeness of Grice's maxims of cooperativity in the case of human‐ machine dialogue.
Conference of the International Speech Communication AssociationAMICA: the AT&t mixed initiative conversational architecture.
51 Citations1997Roberto Pieraccini, Esther Levin +1 more
A task independent oral dialogue model
47 Citations1991Eric Bilange
The model and the designed formalisms used in the implementation of a dialogue manager module inside an oral dialogue system are described and it is shown that the model is able to dialogue on three different applications.
Multi-site data collection and evaluation in spoken language understanding
40 Citations1993Lynette Hirschman, Evelyne Tzoukermann +8 more
This work focuses here on selection of training and test data, evaluation of language understanding, and the continuing search for evaluation methods that will correlate well with expected performance of the technology in applications.
Speech CommunicationPreliminaries to a collaborative model of dialogue
35 Citations1994Philip R. Cohen, Hector J. Levesque
This work sketches here how a formal theory of joint action explains confirmations that arise in task-oriented telephone dialogues, and argues that extensions of this analysis to dialogue more generally will be difficult and force us to give up the authors' simplistic analyses of propositional content and literal meaning.
Edinburgh Research Explorer (University of Edinburgh)Empirical studies in discourse
31 Citations1997Marilyn Walker, Johanna D. Moore
This issue brings together a collection of papers illustrating recent approaches to empirical research in discourse generation and interpretation, and describes an empirical research strategy that leads from empirical findings to general theories.
arXiv (Cornell University)The Use of Knowledge Preconditions in Language Processing
29 Citations1995Karen E. Lochbaum
Effects of variable initiative on linguistic behavior in human-computer spoken natural language dialogue
28 Citations1997Ronnie W. Smith, Steven A. Gordon
Analysis of the dialogue structure of actual human-computer interactions indicates there are differences in user behavior and dialogue structure as a function of the computer's level of initiative, and provides evidence that a spoken natural language dialogue system must be capable of varying itslevel of initiative to facilitate effective interaction with users of varying levels of expertise and experience.
arXiv (Cornell University)On the use of expectations for detecting and repairing human-machine miscommunication
25 Citations1997Morena Danieli
A preliminary evaluation of a large amount of interactions between subjects and DIALOGOS shows that the system performance is enhanced by the uses of both predictions and pragmatic-based expectations.
Systematic design of spoken prompts
25 Citations1996Brian Hansen, David Novick +1 more
A set of heuristics for choosing appropriate prompt styles are presented and it is shown that a set of dimensions can be formulated from theseHeuristics.
Message Understanding Conference (MUC) tests of discourse processing
20 Citations1995Nancy Chinchor, Beth Sundheim
An early attempt to use the results from an information extraction evaluation to provide insight notice relationship between the difficulty of discourse processing and performance on the information extraction task and an upcoming noun phrase coreference evaluation is described.
Human-Computer InteractionAlgorithms for Automatic Dialogue Analysis Using Propositional Production Systems
14 Citations1995Dan R. Olsen, Andrew Monk +1 more
Algorithms and procedures that can be used to automate the analysis of a specification to facilitate this iterative process for properties such as task completeness, reversibility of effect, accessibility, connectedness, and avoidance of deadlock are described.
N.b.: A graphical user interface for annotating spoken dialogue
8 Citations1995Giovanni Flammia, Victor W. Zue
This paper describes how to use N.b. for annotating embedded discourse segments and the system’s end-to-end performance in a transcribed dialogue and presents a graphical user interface for annotated the discourse structure of spoken dialogue.
Learning the structure of mixed initiative dialogues using a corpus of annotated conversations 1
8 Citations1997Giovanni Flammia, Victor W. Zue
An ongoing effort to derive linear discourse structures from a corpus of telephone conversations is reported, to determine how reliably human annotators can tag discourse segments in dialogues and to investigate how to build machine models for performing this annotation task.
Speech CommunicationTowards a theory of belief reconstruction: Application to communication
7 Citations1994Mitja Sadek
A theory of belief reconstruction to be embedded in an agent's communication model, which accounts for both belief persistence and revision and is couched in an autoepistemic logic used objectively along the same lines as in Levesque, 1990.
Spoken Dialogue Understanding and Local Context.
1 Citations1994Peter A. Heeman
It is proposed that this resolution must be and can be done using local context, and so will make a natural language understanding system more robust and able to deal with the unconstrained nature of spoken dialogue.