Computational Models of Miscommunication Phenomena

Purver M, Hough J, Howes C (2018)

Zeitschriftenaufsatz | Veröffentlicht | Englisch
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Purver, Matthew; Hough, JulianUniBi; Howes, Christine
Abstract / Bemerkung
Miscommunication phenomena such as repair in dialogue are important indicators of the quality of communication. Automatic detection is therefore a key step toward tools that can characterize communication quality and thus help in applications from call center management to mental health monitoring. However, most existing computational linguistic approaches to these phenomena are unsuitable for general use in this way, and particularly for analyzing human-human dialogue: Although models of other-repair are common in human-computer dialogue systems, they tend to focus on specific phenomena (e.g., repair initiation by systems), missing the range of repair and repair initiation forms used by humans; and while self-repair models for speech recognition and understanding are advanced, they tend to focus on removal of disfluent material important for full understanding of the discourse contribution, and/or rely on domain-specific knowledge. We explain the requirements for more satisfactory models, including incrementality of processing and robustness to sparsity. We then describe models for self- and other-repair detection that meet these requirements (for the former, an adaptation of an existing repair model; for the latter, an adaptation of standard techniques) and investigate how they perform on datasets from a range of dialogue genres and domains, with promising results. Purver, et al. note that most models of repair in dialogue tend to focus on the system initiating repair, but are not able to detect repair initiated by humans. They develop a repair detection model based on strict incrementalism and parallelism, detecting the match between the turn that is repaired and the turn that is doing the repairing. Their model achieves state-of-the-art performance on most corpora of spoken English.
Miscommunication; Dialogue; Repair; Disfluency; Incrementality; Parallelism; Sparsity
Page URI


Purver M, Hough J, Howes C. Computational Models of Miscommunication Phenomena. TOPICS IN COGNITIVE SCIENCE. 2018;10(2):425-451.
Purver, M., Hough, J., & Howes, C. (2018). Computational Models of Miscommunication Phenomena. TOPICS IN COGNITIVE SCIENCE, 10(2), 425-451. doi:10.1111/tops.12324
Purver, Matthew, Hough, Julian, and Howes, Christine. 2018. “Computational Models of Miscommunication Phenomena”. TOPICS IN COGNITIVE SCIENCE 10 (2): 425-451.
Purver, M., Hough, J., and Howes, C. (2018). Computational Models of Miscommunication Phenomena. TOPICS IN COGNITIVE SCIENCE 10, 425-451.
Purver, M., Hough, J., & Howes, C., 2018. Computational Models of Miscommunication Phenomena. TOPICS IN COGNITIVE SCIENCE, 10(2), p 425-451.
M. Purver, J. Hough, and C. Howes, “Computational Models of Miscommunication Phenomena”, TOPICS IN COGNITIVE SCIENCE, vol. 10, 2018, pp. 425-451.
Purver, M., Hough, J., Howes, C.: Computational Models of Miscommunication Phenomena. TOPICS IN COGNITIVE SCIENCE. 10, 425-451 (2018).
Purver, Matthew, Hough, Julian, and Howes, Christine. “Computational Models of Miscommunication Phenomena”. TOPICS IN COGNITIVE SCIENCE 10.2 (2018): 425-451.

1 Zitation in Europe PMC

Daten bereitgestellt von Europe PubMed Central.

Editors' Introduction: Miscommunication.
Healey PGT, de Ruiter JP, Mills GJ., Top Cogn Sci 10(2), 2018
PMID: 29749040

73 References

Daten bereitgestellt von Europe PubMed Central.

The HCRC map task data
Anderson, Language and Speech 34(4), 1991

Disfluency rates in conversation: effects of age, relationship, topic, role, and gender.
Bortfeld H, Leon SD, Bloom JE, Schober MF, Brennan SE., Lang Speech 44(Pt 2), 2001
PMID: 11575901
How listeners compensate for disfluencies in spontaneous speech
Brennan, Journal of Memory and Language 44(2), 2001

Burnard, 2000

Clark, 2013

Clark, 1996

Colman, 2011
Universal Principles in the Repair of Communication Problems.
Dingemanse M, Roberts SG, Baranova J, Blythe J, Drew P, Floyd S, Gisladottir RS, Kendrick KH, Levinson SC, Manrique E, Rossi G, Enfield NJ., PLoS ONE 10(9), 2015
PMID: 26375483
Classifying ellipsis in dialogue: A machine learning approach
Fernández, Computational Linguistics 33(3), 2007
Disfluencies, language comprehension, and tree adjoining grammars
Ferreira, Cognitive Science 28(5), 2004
Clarification, ellipsis, and the nature of contextual updates in dialogue
Ginzburg, Linguistics and Philosophy 27(3), 2004

Ginzburg, 2007

Godfrey, 1992

Goodwin, 1979

Gravano, 2009

Healey, 2005

Healey, 2013

Healey, 2015

Hjalmarsson, 2012
Joint incremental disfluency detection and dependency parsing
Honnibal, Transactions of the Association of Computational Linguistics (TACL) 2(), 2014

Hough, 2015

Hough, 2012

Hough, 2013

Hough, 2014


Howes, 2014

Howes, 2017
On incrementality in dialogue: Evidence from compound contributions
Howes, Dialogue & Discourse 2(1), 2011

Howes, 2012

Johnson, 2004

Detection and recognition of correction utterances on misrecognition 721 of spoken dialog system
Kitaoka, Systems and Computers in Japan 36(11), 2005
Recognizing disfluencies in conversational speech
Lease, Audio, Speech, and Language Processing, IEEE Transactions on 14(5), 2006
Multithreaded context for robust conversational interfaces: Context-sensitive speech recognition and interpretation of corrective fragments
Lemon, ACM Transactions on Computer-Human Interaction 11(3), 2004
Monitoring and self-repair in speech.
Levelt WJ., Cognition 14(1), 1983
PMID: 6685011

Levelt, 1989

Lickley, 2001
Characterizing and predicting corrections in spoken dialogue systems
Litman, Computational Linguistics 32(3), 2006

Lopes, 2015

Shared understanding in psychiatrist-patient communication: association with treatment adherence in schizophrenia.
McCabe R, Healey PG, Priebe S, Lavelle M, Dodwell D, Laugharne R, Snell A, Bremner S., Patient Educ Couns 93(1), 2013
PMID: 23856552


Mieskes, 2006

Mikolov, 2013

Mills, 2013

Mills, 2006
Doctor-patient communication: a review of the literature.
Ong LM, de Haes JC, Hoos AM, Lammes FB., Soc Sci Med 40(7), 1995
PMID: 7792630
Predicting spoken disfluencies during human-computer interaction
Oviatt, Computer Speech & Language 9(1), 1995

Purver, 2003

Rasooli, 2014

Raux, 2005

Rieser, 2005

Rodríguez, 2004

San-Segundo, 2001
The preference for self-correction in the organization of repair in conversation
Schegloff, Language 53(2), 1977

Schlangen, 2005

Shriberg, 1994

Skantze, 2010
A coding scheme for question-response sequences in conversation
Stivers, Journal of Pragmatics 42(10), 2010
Dialogue act modeling for automatic tagging and recognition of conversational speech
Stolcke, Computational Linguistics 26(3), 2000

Concept type prediction and responsive adaptation in a dialogue system
Stoyanchev, Dialogue & Discourse 3(1), 2012

Surendran, 2006

Toutanova, 2003

Turian, 2010

Weng, 2007
POMDP-based statistical spoken dialog systems: A review
Young, Proceedings of the IEEE 101(5), 2013

Zwarts, 2010

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

PMID: 29517153
PubMed | Europe PMC

Suchen in

Google Scholar