A Distributional Semantics Approach to Implicit Language Learning

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that the implicit learnability of semantic regularities depends on the degree to which the relevant concept is reflected in language use. In our simulations, we train a Vector-Space model on either an English or a Chinese corpus and then feed the resulting representations to a feed-forward neural network. The task of the neural network was to find a mapping between the word representations and the novel words. Using datasets from four behavioural experiments, which used different semantic manipulations, we were able to obtain learning patterns very similar to those obtained by humans.