Disfluency prediction in natural spoken language

to connected objects

Abstract: Until recently, disfluencies in human language were outside of the focus of linguistic research. However, with the advent of technologies such as digital personal assistants, this approach changed. In order to mimic natural conversation, it is necessary to create a natural sounding output, including phenomena deemed undesirable in an idealized view of the language, such as disfluencies. This thesis presents two novel approaches to disfluency prediction. It extends the list of known predictors of disfluencies with surprisal, a measure of processing complexity derived from psycholinguistic and information-theoretic observations. Additionally, it presents a computational-linguistic approach in which a machine translation architecture (encoder-decoder) is used for the prediction of disfluencies

Location
Deutsche Nationalbibliothek Frankfurt am Main
Extent
Online-Ressource
Language
Englisch
Notes
Universität Freiburg, Dissertation, 2019

Keyword
Englisch
Maschinelles Lernen
Verzögerungsphänomen
Korpus
Informationstheorie

Event
Veröffentlichung
(where)
Freiburg
(who)
Universität
(when)
2021
Creator
Contributor

DOI
10.6094/978-3-928969-84-0
URN
urn:nbn:de:bsz:25-freidok-2197227
Rights
Kein Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Last update
21.03.2025, 12:12 AM CET

Data provider

This object is provided by:
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Show original at data provider

Associated

Time of origin

  • 2021

Other Objects (12)

The neverending sentence: rightward expansion in spoken language

The neverending sentence: rightward expansion in spoken language

Human-like natural language generation in spoken dialogue systems

Human-like natural language generation in spoken dialogue systems

À nouveau and de nouveau in spoken and written French

À nouveau and de nouveau in spoken and written French

Statistical methods in natural language understanding and spoken dialogue systems

Hochschulschrift

Statistical methods in natural language understanding and spoken dialogue systems

Statistical inferences for polarity identification in natural language

Statistical inferences for polarity identification in natural language

DIGGER-Bac: prediction of seed regions for high-fidelity construction of synthetic small RNAs in bacteria

DIGGER-Bac: prediction of seed regions for high-fidelity construction of synthetic small RNAs in bacteria

The attitudinal meaning of preverbal markers in Gascon: Insights from the analysis of literary and spoken language data

The attitudinal meaning of preverbal markers in Gascon: Insights from the analysis of literary and spoken language data

Handbook of standards and resources for spoken language systems, Vol. 2.. Spoken language characterisation

Handbook of standards and resources for spoken language systems, Vol. 2.. Spoken language characterisation

Robust peer prediction mechanisms

Hochschulschrift

Robust peer prediction mechanisms

Handbook of standards and resources for spoken language systems, Vol. 4.. Spoken language reference materials

Handbook of standards and resources for spoken language systems, Vol. 4.. Spoken language reference materials

Handbook of standards and resources for spoken language systems, Vol. 3.. Spoken language system assessment

Handbook of standards and resources for spoken language systems, Vol. 3.. Spoken language system assessment

Italian in Toronto : : a preliminary comparative study on language use and language maintenance

Italian in Toronto : : a preliminary comparative study on language use and language maintenance

Related objects