Graph-based model for lexical category acquisition

We present a novel approach for discovering word categories, sets of words sharing a significant aspect of distributional context. We determine symmetric similarity of word pair, lexical category is then created based on graph-partitioning method. We train our model on a corpus of child-directed speech from CHILDES and show that the model successful learns word categories. Furthermore, a number of different measures have been proposed for evaluating computational models of category acquisition. In this paper, we propose a new measure that meets three criteria: informativeness, diversity and purity.