H. Fukś and C. Phipps (Canada)
Modelling and simulation methodologies, language acqui sition, random graphs, complex networks
We demonstrate how the paradigm of complex networks can be used to model some aspects of the process of sec ond language acquisition. When learning a new language, knowledge of 3000-4000 of the most frequent words ap pears to be a significant threshold, necessary to transfer reading skills from L1 to L21 . We show that this thresh old corresponds to the transition from Zipf’s law to a non Zipfian regime in the rank-frequency plot of words of the English language. Using a large dictionary, we then con struct a graph representing this dictionary, and study topo logical properties of subgraphs generated by the k most fre quent words of the language. The clustering coefficient of these subgraphs reaches a minimum in the same place as the crossover point in the rank-frequency plot. We conjec ture that the coincidence of all these thresholds may indi cate a change in the language structure, which occurs when the vocabulary size reaches about 3000-4000 words.
Important Links:
Go Back
