A Probabilistic Incremental Model of Word Learning in the Presence of Referential Uncertainty

We present a probabilistic incremental model of early word learning. The model acquires the meaning of words from exposure to word usages in sentences, paired with appropriate semantic representations, in the presence of referential uncertainty. A distinct property of our model is that it continually revises its learned knowledge of a word’s meaning, but over time converges on the most likely meaning of the word. Another key feature is that the model bootstraps its own partial knowledge of word–meaning associations to help more quickly learn the meanings of novel words. Results of simulations on naturalistic child-directed data show that our model exhibits behaviours similar to those observed in the early lexical acquisition of children, such as vocabulary spurt and fast mapping.