Dirichlet Process Mixture Models for lexical category acquisition

In this work, we apply Dirichlet Process Mixture Models (DPMMs) to a cognitive computational task in natural language processing (NLP): lexical category acquisition. The model takes a corpus of child-directed speech from CHILDES as input. We assess the performance using a new measure we proposed that meets three criteria: informativeness, diversity and purity. The quantitative and qualitative evaluation performed highlights the choice of the feature dimension and inherent parameters can influence the performance of DPMMs towards lexical category solutions.