|
<term>
long distance constraints
</term>
in
|
a
|
<term>
sentence
</term>
or
<term>
paragraph
</term>
|
#21227
This paper introduces a simple mixture language model that attempts to capture long distance constraints in a sentence or paragraph. |
|
</term>
. The models were constructed using
|
a
|
5K
<term>
vocabulary
</term>
and trained using
|
#21247
The models were constructed using a 5K vocabulary and trained using a 76 million word Wall Street Journal text corpus. |
|
<term>
vocabulary
</term>
and trained using
|
a
|
76 million
<term>
word
</term><term>
Wall Street
|
#21253
The models were constructed using a 5K vocabulary and trained using a 76 million word Wall Street Journal text corpus. |
|
recognition system
</term>
, experiments show
|
a
|
7 % improvement in
<term>
recognition accuracy
|
#21271
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. |
|
trigram models
</term>
as compared to using
|
a
|
<term>
trigram model
</term>
. This paper describes
|
#21287
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. |
|
trigram model
</term>
. This paper describes
|
a
|
method of
<term>
detecting speechrepairs
</term>
|
#21294
This paper describes a method of detecting speechrepairs that uses a part-of-speech tagger. |
|
<term>
detecting speechrepairs
</term>
that uses
|
a
|
<term>
part-of-speech tagger
</term>
. The
<term>
|
#21301
This paper describes a method of detecting speechrepairs that uses a part-of-speech tagger. |
|
speechrepairs
</term>
, and so is able to mark
|
a
|
<term>
transition
</term>
either as a
<term>
|
#21322
The tagger is given knowledge about category transitions for speechrepairs, and so is able to mark a transition either as a likely repair or as fluent speech. |
|
to mark a
<term>
transition
</term>
either as
|
a
|
<term>
likely repair
</term>
or as
<term>
fluent
|
#21326
The tagger is given knowledge about category transitions for speechrepairs, and so is able to mark a transition either as a likely repair or as fluent speech. |
|
understanding technology
</term>
is implemented in
|
a
|
system called
<term>
IDUS ( Intelligent Document
|
#21395
Our document understanding technology is implemented in a system called IDUS (Intelligent Document Understanding System), which creates the data for a text retrieval application and the automatic generation of hypertext links. |
|
System )
</term>
, which creates the data for
|
a
|
<term>
text retrieval application
</term>
and
|
#21411
Our document understanding technology is implemented in a system called IDUS (Intelligent Document Understanding System), which creates the data for a text retrieval application and the automatic generation of hypertext links. |