D12-1059 |
categories induced by online LDA in the
|
word learning
|
model . The fourth condition
|
D12-1059 |
in a crosssituational model of
|
word learning
|
have been rare . Here we adopt
|
D12-1059 |
mechanisms have been proposed for
|
word learning
|
. One well-studied mechanism
|
D12-1059 |
explore the role of syntax in
|
word learning
|
. Maurits et al. ( 2009 ) investigates
|
D12-1059 |
contribution of lexical categories to
|
word learning
|
in a more realistic scenario
|
D12-1059 |
assumption unreasonably simplifies the
|
word learning
|
problem . To investigate the
|
D12-1059 |
mappings , we compare the pattern of
|
word learning
|
over time in four con - ditions
|
D12-1059 |
category-based alignment in the
|
word learning
|
model by setting A ( w ) = 1
|
D12-1059 |
cate - gories . We then evaluated
|
word learning
|
on Anne . We chose the parameters
|
D12-1059 |
at hand , that is , improving
|
word learning
|
by using the sentential context
|
D12-1059 |
performance of a cross-situational
|
word learning
|
model . For this purpose , we
|
D12-1059 |
his model of crosssituational
|
word learning
|
, showing that they can improve
|
D12-1059 |
assumption that prior to the onset of
|
word learning
|
, the categorization module has
|
D12-1059 |
verbs and nouns ) can indeed help
|
word learning
|
in a more naturalistic incremental
|
D12-1059 |
learning module with a probabilistic
|
word learning
|
model . Our results show that
|
D12-1059 |
from the utterance ( only for the
|
word learning
|
module ) . In order to simulate
|
D12-1059 |
and Anne and then started the
|
word learning
|
module for the Anne portion while
|
D12-1059 |
existing probabilistic model of
|
word learning
|
which combines cross-situational
|
D12-1059 |
using these categories can improve
|
word learning
|
compared to not using them and
|
D12-1059 |
we investigate the interplay of
|
word learning
|
and category induction by integrating
|