Modeling human performance in statistical word segmentation

Frank, Michael C.; Goldwater, Sharon; Griffiths, Thomas L.; Tenenbaum, Joshua B.

doi:10.1016/j.cognition.2010.07.005

Cited by 154 publications

(214 citation statements)

References 37 publications

(14 reference statements)

Supporting

Mentioning

198

Contrasting

Order By: Relevance

“…Word learning: Xu and Tenenbaum (2007b) ;Andrews, Vigliocco, and Vinson (2009) ;Frank, Goodman, and Tenenbaum (2009) 16. Word segmentation : Goldwater, Griffiths, and Johnson (2007) ;Frank, Goldwater, Griffiths, and Tenenbaum (2007) A. 3 …”

Section: A2 Applicationsmentioning

confidence: 99%

A tutorial introduction to Bayesian models of cognitive development

et al. 2011

Self Cite

View full text Add to dashboard Cite

We present an introduction to Bayesian inference as it is used in probabilistic models of cognitive development. Our goal is to provide an intuitive and accessible guide to the what, the how, and the why of the Bayesian approach: what sorts of problems and data the framework is most relevant for, and how and why it may be useful for developmentalists. We emphasize a qualitative understanding of Bayesian inference, but also include information about additional resources for those interested in the cognitive science applications, mathematical foundations, or machine learning details in more depth. In addition, we discuss some important interpretation issues that often arise when evaluating Bayesian models in cognitive science.

show abstract

Section: A2 Applicationsmentioning

confidence: 99%

A tutorial introduction to Bayesian models of cognitive development

et al. 2011

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the work of Frank et al (2007Frank et al ( , 2010, the authors examine the predictions of Goldwater et al's unigram word segmentation model, as well as that of several other models, and compare these predictions to human performance in several experiments. 8 The experiments are modeled on those of Saffran et al (1996), and involve segmenting words from an artificial language based on exposure to utterances containing no pauses or other acoustic cues to word boundaries.…”

Section: Seethekitty Lookatthekitty S E E T H E K I T T Y L O O K mentioning

confidence: 99%

“…If so, then we have helped to explain why humans behave in this way --it is the optimal response to the data they are exposed to. If not, then we can begin to investigate how and why humans might differ from the optimal behavior (Goldwater et al 2009, Frank et al 2010.…”

Section: Bayesian Modeling As a Computational-level Approachmentioning

confidence: 99%

Statistical Learning, Inductive Bias, and Bayesian Inference in Language Acquisition

Pearl¹,

Goldwater²

2016

Oxford Handbooks Online

Self Cite

View full text Add to dashboard Cite

Bayesian models of language acquisition are powerful tools for exploring how linguistic generalizations can be made. Notably, Bayesian models assume children leverage statistical information in sophisticated ways, and so it is important to demonstrate that children’s behavior is consistent with both the assumptions of the Bayesian framework and the predictions of specific models. We first provide a historical overview of behavioral evidence suggesting children utilize available statistical information to make useful generalizations in a variety of tasks. We then discuss the Bayesian modeling framework, including benefits of particular interest to both developmental and theoretical linguists. We conclude with a review of several case studies that demonstrate how Bayesian models can be applied to problems of interest in language acquisition.

show abstract

“…More recently, unsupervised methods, in particular, Bayesian methods like Dirichlet processes (Goldwater et al 2009), have been investigated that learn to segment by way of learning an inventory of words. Frank et al (2007) provide a review and a comparison of some related segmentation models with experimental results from an artificial language learning task with adults.…”

Section: Approaches To Segmentation Based On Representations Of the Amentioning

confidence: 99%

A Computational Model of Unsupervised Speech Segmentation for Correspondence Learning

Duran

Schütze

Möbius

et al. 2010

Res on Lang and Comput

View full text Add to dashboard Cite

In this paper, we develop a new conceptual framework for an important problem in language acquisition, the correspondence problem: the fact that a given utterance has different manifestations in the speech and articulation of different speakers and that the correspondence of these manifestations is difficult to learn. We put forward the Correspondence-by-Segmentation Hypothesis, which states that correspondence is primarily learned by first segmenting speech in an unsupervised manner and then mapping the acoustics of different speakers onto each other. We show that a rudimentary segmentation of speech can be learned in an unsupervised fashion. We then demonstrate that, using the previously learned segmentation, different instances of a word can be mapped onto each other with high accuracy when trained on utterance-label pairs for a small set of words.

show abstract

Modeling human performance in statistical word segmentation

Cited by 154 publications

References 37 publications

A tutorial introduction to Bayesian models of cognitive development

A tutorial introduction to Bayesian models of cognitive development

Statistical Learning, Inductive Bias, and Bayesian Inference in Language Acquisition

A Computational Model of Unsupervised Speech Segmentation for Correspondence Learning

Contact Info

Product

Resources

About