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 investigate the effects of allowing some words and referents to appear more often than others, as is true in real learning environments. More frequent wordreferent pairs are often—but not always—learned better, and also boost learning of other pairs. Superior learning for training sets with varying pair frequency may be a result of learning frequent pairs first, and using this knowledge to reduce ambiguity in later trials to learn other items. However, contextual diversity – the number of other pairs a given pair appears with – is naturally confounded with frequency, and presents an alternative explanation. The experiments in the present study systematically manipulate three critical factors in cross-situational learning – frequency, contextual diversity, and within-trial ambiguity – and measure their individual and combined effects on statistical word learning.

Abstract not found

Recent work has led to the ability to perform space efficient, approximate counting over large vocabularies in a streaming context. Motivated by the existence of data structures of this type, we explore the computation of associativity scores, otherwise known as pointwise mutual information (PMI), in a streaming context. We give theoretical bounds showing the impracticality of perfect online PMI computation, and detail an algorithm with high expected accuracy. Experiments on news articles show our approach gives high accuracy on real world data. 1

This paper presents an incremental probabilistic learner that models the acquistion of syntax and semantics from a corpus of child-directed utterances paired with possible representations of their meanings. These meaning representations approximate the contextual input available to the child; they do not specify the meanings of individual words or syntactic derivations. The learner then has to infer the meanings and syntactic properties of the words in the input along with a parsing model. We use the CCG grammatical framework and train a non-parametric Bayesian model of parse structure with online variational Bayesian expectation maximization. When tested on utterances from the CHILDES corpus, our learner outperforms a state-of-the-art semantic parser. In addition, it models such aspects of child acquisition as “fast mapping,” while also countering previous criticisms of statistical syntactic learners. 1

Previous research shows that human learners can acquire word-referent pairs over a short series of individually ambiguous situations each containing multiple words and referents (Yu & Smith, 2007). In this kind of cross-situational statistical learning based on the repeated co-occurrence of words with their intended referents, the application of principles such as mutual exclusivity and contrast can leverage prior experience to reduce the complexity in situations with multiple words and multiple referents. However, these principles can also block the learning of oneto-many mappings. In a study analogous those done in traditional associative learning, we manipulate the early and late evidence for particular pairings in the cross-situational learning paradigm, and examine the effects on learning of both one-to-one and many-to-many mappings. Two major findings are: 1) participants use mutual exclusivity and contrast to facilitate learning; and 2) given sufficient evidence, learners can adaptively disregard these principles and learn many-to-many mappings.

This paper presents a computational model of word learning with the goal to understand the mechanisms through which word learning is grounded in multimodal social interactions between young children and their parents. We designed and implemented a novel multimodal sensing environment consisting of two head-mounted mini cameras that are placed on both the child’s and the parent’s foreheads, motion tracking of head and hand movements and recording of caregiver’s speech. Using this new sensing technology, we captured the dynamic visual information from both the learner’s perspective and the parent’s viewpoint while they were engaged in a free-play toy-naming interaction. We next implemented various data processing programs that automatically extracted visual, motion and speech features from raw sensory data. A probabilistic model was developed that can predict the child’s learning results based on sensorimotor features extracted from child-parent interaction. More importantly, through the trained regression coefficients in the model, we discovered a set of perceptual and motor patterns that are informatively time-locked to words and their intended referents and predictive of word learning. Those patterns provide quantitative measures of the roles of various sensorimotor cues that may facilitate word learning, which sheds lights on understanding the underlying real-time learning mechanisms in child-parent social interactions.

Late talkers (LTs)—children who show a marked delay in vocabulary learning—are at risk for Specific Language Impairment (SLI), and much research has focused on identifying factors contributing to this phenomenon. We use a computational model of word learning to further shed light on these factors. In particular, we show that variations in the attentional abilities of the computational learner can be used to model various identified differences in LTs compared to normally-developing children: delayed and slower vocabulary growth, greater difficulty in novel word learning, and decreased semantic connectedness among learned words.

Abstract not found

Learning the meaning of words from ambiguous and noisy context is a challenging task for language learners. It has been suggested that children draw on syntactic cues such as lexical categories of words to constrain potential referents of words in a complex scene. Although the acquisition of lexical categories should be interleaved with learning word meanings, it has not previously been modeled in that fashion. In this paper, we investigate the interplay of word learning and category induction by integrating an LDA-based word class learning module with a probabilistic word learning model. Our results show that the incrementally