Rapid Word Learning Under Uncertainty via Cross-Situational Statistics

By Chen Yu, Linda B. Smith. Psychology Science, 2007

625 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology

View Paper: https://www.semanticscholar.org/paper/a0bd9fc1141228e42afb2e778869469cdf60450d

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

Citations in the corpus

Learning Words from Images and Speech (2014, background): “Here, we explore the possibility of learning both an acoustic model and a word/image association from multi-modal co-occurrences between speech and pictures alone (a task known as cross-situational learning [2]).”
Word learning emerges from the interaction of online referent selection and slow associative learning (2012, positive): “If this is done in small increments over multiple naming events, the more consistent ones could rise to the top, as in cross-situational learning (Smith & Yu, 2008; Yu & Smith, 2007).”
Statistical word learning at scale: the baby's view is better. (2013, positive): “…months of age (Mayor & Plunkett, 2011), many have argued that this learning cannot emerge from just the unambiguous naming events that children experience, but must also reflect the integration of information from less informative events (e.g. Siskind, 1996; Yu & Smith, 2007; Blythe et al., 2010).”
Infants rapidly learn word-referent mappings via cross-situational statistics. (2008, background): “The learner could solve this learning task via simple (or not so simple, see Kruschke, 2001; Kruschke, Kappenman , & Hetrick, 2005; Yu & Smith, 2007; Yu et al., 2007) associative learning mechanisms .”
Predicting the birth of a spoken word (2015, background): “Higher use frequency may allow children to make more accurate inferences about noun meaning just by virtue of increased contextual cooccurrence (25, 26).”
Multisensory perception as an associative learning process (2014, background): “Yet, Smith and Yu (2007, 2008) and Yu and Smith (2006, 2007, 2011, 2012) show how the binding of a word and a referent occurs through an associative learning process whereby infants and adults learn, across varying contexts, the statistical likelihood that a word refers to a particular kind of…”
PSYCHOLOGICAL SCIENCE Research Article Using Speakers ’ Referential Intentions to Model Early Cross-Situational Word Learning (positive): “Combined with the demonstration that adults and infants are able to use some sort of statistical information in cross-situational learning tasks (Smith & Yu, 2008; Yu & Smith, 2007 ), the success of our model and others suggests that it is not necessary to posit domain-specific principles to accoun”
Integrating experiential and distributional data to learn semantic representations. (2009, background): “Recently, studies such as, for example, Yu and Smith (2007) and L. B. Smith and Yu (2008) have shown how statistical regularities between the co-occurrences of words and the co-occurrences of their referents can facilitate the learning of word–object mappings, and others such as, for example, Roy…”
Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech (2017, background): “Cognitive scientists have long been interested in how infants use sensory input to learn the mapping of words to real-world entities (Yu and Smith, 2007; Cunillera et al., 2010; Thiessen, 2010), with computational models providing one way to specify and test theories.”
The Novel Object and Unusual Name (NOUN) Database: A collection of novel images for use in experimental research (2016, background): “…which participants—both adults and children—are taught names for objects either explicitly, for instance, through the use of social cues and ostensive feedback (Gauthier & Tarr, 1997; Horst & Samuelson, 2008) or implicitly across several encounters (e.g., Axelsson & Horst, 2014; Yu & Smith, 2007).”
Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner (2016, positive): “…transition probability (Saffran, Aslin, & Newport, 1996; Daland & Pierrehumbert, 2011), word meaning learning based on cross situational statistics (Yu & Smith, 2007; K. Smith, Smith, & Blythe, 2011; Siskind, 1996), semantic role learning based on syntactic cues (Connor, Fisher, & Roth, 2013), etc.”
Social and Discourse Contributions to the Determination of Reference in Cross-Situational Word Learning (2013, background): “Unsurprisingly, for a word learner guessing the meaning of a novel noun, the best guess will likely be that the word refers to an object that is present (Pinker, 1989; Yu & Smith, 2007; Siskind, 1996).”