Exploring the Robustness of Cross-Situational Learning Under Zipfian Distributions

@article{Vogt2012ExploringTR,
  title={Exploring the Robustness of Cross-Situational Learning Under Zipfian Distributions},
  author={Paul Vogt},
  journal={Cognitive science},
  year={2012},
  volume={36 4},
  pages={
          726-39
        }
}
  • P. Vogt
  • Published 1 May 2012
  • Psychology
  • Cognitive science
Cross-situational learning has recently gained attention as a plausible candidate for the mechanism that underlies the learning of word-meaning mappings. In a recent study, Blythe and colleagues have studied how many trials are theoretically required to learn a human-sized lexicon using cross-situational learning. They show that the level of referential uncertainty exposed to learners could be relatively large. However, one of the assumptions they made in designing their mathematical model is… 

Figures from this paper

Cross-situational learning in a Zipfian environment
TLDR
This work shows the opposite of the predicted effect using cross-situational learning experiments with adults: when the distribution of words and meanings is Zipfian, learning is not impaired and is usually improved.
Cross-situational learning of large lexicons with finite memory
TLDR
The main finding is that it is possible for this learner to acquire a human-scale lexicon by adulthood with word-exposure and memory-decay rates that are consistent with empirical research on childhood word learning, as long as the degree of referential uncertainty is not too high or the learner employs a mutual exclusivity constraint.
Reinforcement and inference in cross-situational word learning
TLDR
An adaptive learning algorithm is proposed that contains a parameter that controls the strength of the reinforcement applied to associations between concurrent words and referents, and aparameter that regulates inference, which includes built-in biases, such as mutual exclusivity, and information of past learning events.
Mechanisms of Cross-situational Learning: Behavioral and Computational Evidence.
A Bootstrapping Model of Frequency and Context Effects in Word Learning
TLDR
This study investigates the effects of allowing some word-referent pairs to appear more frequently than others, as is true in real-world learning environments, and explains how mixing pairs of different frequencies can bootstrap late learning of the low-frequency pairs based on early learning of higher frequency pairs.
Modeling individual performance in cross-situational word learning
TLDR
It is found that the associative model better captures the full range of individual differences and conditions when learning is cross-situational, although the hypothesis testing approach outperforms it when there is no referential ambiguity during training.
Lingodroids: Cross-Situational Learning for Episodic Elements
TLDR
It is demonstrated that cross-situational learning resolves the issues of referential uncertainty for bootstrapping a language for episodic space and time; therefore removing the need to specify the underlying sensors or representations a priori.
Adults Use Distributional Statistics for Word Learning in a Conservative Way
—This study examined how much adults rely on cross- situational information for word learning by comparing their gaze behavior in a word learning task with (computational) models of alternative
The role of partial knowledge in statistical word learning
TLDR
Three experiments are presented that test and verify claims that partial knowledge of some words speed the acquisition of others and construct and compare computational models embodying each of these hypotheses and show that the latter provides a better explanation of the empirical data.
Adults Use Cross-Situational Statistics for Word Learning in a Conservative Way
TLDR
This paper examined how much adults rely on cross-situational information in word learning by comparing their gaze behavior in a word learning task with models of four learning strategies, and manipulated the input type of situations and the co-occurrence frequencies between words and objects to infer correct word-object mappings.
...
...

References

SHOWING 1-10 OF 48 REFERENCES
Learning Times for Large Lexicons Through Cross-Situational Learning
TLDR
Results indicate that there is no necessary link between the ability to learn individual words rapidly and the capacity to acquire a large lexicon, and suggests that cross-situational word learning cannot be ruled out on the basis that it predicts unreasonably long lexicon learning times.
A computational study of cross-situational techniques for learning word-to-meaning mappings
Frequency and Contextual Diversity Effects in Cross-Situational Word Learning
Prior research has shown that people can use the cooccurrence statistics of words and referents in ambiguous situations to learn word meanings during a brief training period. The present studies
A Probabilistic Computational Model of Cross-Situational Word Learning
TLDR
A novel computational model of early word learning is presented to shed light on the mechanisms that might be at work in this process, and demonstrates that much about word meanings can be learned from naturally occurring child-directed utterances, without using any special biases or constraints.
A Bayesian Framework for Cross-Situational Word-Learning
TLDR
A Bayesian model of cross-situational word learning is presented and an extension of this model that also learns which social cues are relevant to determining reference is extended, finding it performs better than competing models.
Integrating Syntactic Knowledge into a Model of Cross-situational Word Learning
TLDR
A probabilistic model of word learn- ing which integrates cross-situational evidence and the knowledge of lexical categories into a single learning mechanism is presented.
A unified model of early word learning: Integrating statistical and social cues
The child as word learner
concepts of reference point and polarity, which presuppose concepts of dimension of comparison and zero point. These concepts can be probed nonlinguistically. For example, animals can be taught to
Weaving a Lexicon
The studies in Weaving a Lexicon make a significant contribution to the growing field of lexical acquisition by considering the multidimensional way in which infants and children acquire the lexicon
...
...