Estimating the latent number of types in growing corpora with reduced cost–accuracy trade-off

What is it about?

In studies of language development, the number of words that a child knows is one of primary indices for their language facility. This paper is about how to "count" the number of words which a child has never spoken before. The paper proposes a statistical technique to estimate such a number of never-spoken-before words. It also provides two case studies to which this method is applied, and showed the proposed method successfully estimate the number of latent words by the data.

Featured Image