|
<term>
incremental grammar development
</term>
|
using
|
an
<term>
extended DCG formalism
</term>
.
|
#21107
We present LHIP, a system for incremental grammar developmentusing an extended DCG formalism. |
|
systems still treat
<term>
coordination
</term>
|
using
|
adapted
<term>
parsing strategies
</term>
,
|
#21150
Despite the large amount of theoretical work done on non-constituent coordination during the last two decades, many computational systems still treat coordinationusing adapted parsing strategies, in a similar fashion to the SYSCONJ system developed for ATNs. |
|
models
</term>
. The models were constructed
|
using
|
a 5K
<term>
vocabulary
</term>
and trained
|
#21246
The models were constructed using a 5K vocabulary and trained using a 76 million word Wall Street Journal text corpus. |
|
using a 5K
<term>
vocabulary
</term>
and trained
|
using
|
a 76 million
<term>
word
</term><term>
Wall
|
#21252
The models were constructed using a 5K vocabulary and trained using a 76 million word Wall Street Journal text corpus. |
|
mixture trigram models
</term>
as compared to
|
using
|
a
<term>
trigram model
</term>
. This paper
|
#21286
Using the BU recognition system, experiments show a 7% improvement in recognition accuracy with the mixture trigram models as compared to using a trigram model. |