Summary: Online Entropy-based Model of Lexical Category Acquisition
Grzegorz Chrupala
Saarland University
gchrupala@lsv.uni-saarland.de
Afra Alishahi
Saarland University
afra@coli.uni-saarland.de
Abstract
Children learn a robust representation of
lexical categories at a young age. We pro-
pose an incremental model of this process
which efficiently groups words into lexi-
cal categories based on their local context
using an information-theoretic criterion.
We train our model on a corpus of child-
directed speech from CHILDES and show
that the model learns a fine-grained set
of intuitive word categories. Furthermore,
we propose a novel evaluation approach
by comparing the efficiency of our induced

Source: Alishahi, Afra - Department of Computational Linguistics and Phonetics, Universität des Saarlandes

Collections: Computer Technologies and Information Sciences