Statistical word learning at scale: the baby's view is better.

By Daniel Yurovsky, Linda B. Smith, Chen Yu. 2013

154 citations recorded by the source corpus.

A key question in early word learning is how children cope with the uncertainty in natural naming events. One potential mechanism for uncertainty reduction is cross-situational word learning – tracking word/object co-occurrence statistics across naming events. But empirical and computational analyses of cross-situational learning have made strong assumptions about the nature of naming event ambiguity, assumptions that have been challenged by recent analyses of natural naming events. This paper shows that learning from ambiguous natural naming events depends on perspective. Natural naming events from parent–child interactions were recorded from both a third-person tripod-mounted camera and from a head-mounted camera that produced a ‘child’s-eye’ view. Following the human simulation paradigm, adults were asked to learn artificial language labels by integrating across the most ambiguous of these naming events. Significant learning was found only from the child’s perspective, pointing to the importance of considering statistical learning from an embodied perspective.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Developmental and Educational Psychology

In Cognitive Science & Psychology

Citations in the corpus

Environmental drivers of systematicity and generalization in a situated agent (2019, background): “…in artiﬁcial neural networks if those networks are afforded access to a rich, interactive, multimodal stream of stimuli that better matches the experience of an embodied human learner (Clerkin et al., 2017; Kellman & Arterberry, 2000; James et al., 2014; Yurovsky et al., 2013; Anderson, 2003).”
The effects of parent-implemented language interventions on child linguistic outcomes: A meta-analysis (2020, methodology): “Please cite this article in press as: Heidlage, J. K., et al. The effects of outcomes: A meta-analysis. Early Childhood Research Quarterly (2019) f child and adult outcomes and the relatively small sample of tudies, the dependent measures were converted to a Hedges’ g tandardized mean difference, co”
Incremental Object Learning From Contiguous Views (2019, methodology): “We began by targeting a core set of 30 speciﬁc object categories [49] that are frequently used in research with infants, identifying the best 3D model instance for each one.”
SAYCam: A Large, Longitudinal Audiovisual Dataset Recorded From the Infant’s Perspective (2020, background): “…of view, allowing researchers to not simply observe the visual stimuli surrounding a child, but also access the visual stimuli that is actually available to a child (see Yurovsky et al., 2013, for an example of how this first-person perspective can lead to novel insights into learning mechanisms).”