tech,0-2-H92-1026,bq |
</term>
to resolve
<term>
ambiguity
</term>
.
<term>
|
HBG
|
</term>
incorporates
<term>
lexical , syntactic
|
#18919
We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity.HBG incorporates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way. |
lr,10-3-H92-1026,bq |
bracketed sentences
</term>
, called a
<term>
|
Treebank
|
</term>
, in combination with
<term>
decision
|
#18953
We use a corpus of bracketed sentences, called aTreebank, in combination with decision tree building to tease out the relevant aspects of a parse tree that will determine the correct parse of a sentence. |
model,3-1-H92-1026,bq |
<term>
accuracy
</term>
. We describe a
<term>
|
generative probabilistic model of natural language
|
</term>
, which we call
<term>
HBG
</term>
,
|
#18896
We describe agenerative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. |
other,26-3-H92-1026,bq |
tease out the relevant aspects of a
<term>
|
parse tree
|
</term>
that will determine the correct
<term>
|
#18969
We use a corpus of bracketed sentences, called a Treebank, in combination with decision tree building to tease out the relevant aspects of aparse tree that will determine the correct parse of a sentence. |
other,36-3-H92-1026,bq |
the correct
<term>
parse
</term>
of a
<term>
|
sentence
|
</term>
. This stands in contrast to the
|
#18979
We use a corpus of bracketed sentences, called a Treebank, in combination with decision tree building to tease out the relevant aspects of a parse tree that will determine the correct parse of asentence. |
lr,3-3-H92-1026,bq |
process
</term>
in a novel way . We use a
<term>
|
corpus of bracketed sentences
|
</term>
, called a
<term>
Treebank
</term>
,
|
#18946
We use acorpus of bracketed sentences, called a Treebank, in combination with decision tree building to tease out the relevant aspects of a parse tree that will determine the correct parse of a sentence. |
tech,13-1-H92-1026,bq |
natural language
</term>
, which we call
<term>
|
HBG
|
</term>
, that takes advantage of detailed
|
#18906
We describe a generative probabilistic model of natural language, which we callHBG, that takes advantage of detailed linguistic information to resolve ambiguity. |
tech,17-5-H92-1026,bq |
parsing models
</term>
, which we call
<term>
|
P-CFG
|
</term>
, the
<term>
HBG model
</term>
significantly
|
#19024
In head-to-head tests against one of the best existing robust probabilistic parsing models, which we callP-CFG, the HBG model significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error. |
other,33-3-H92-1026,bq |
</term>
that will determine the correct
<term>
|
parse
|
</term>
of a
<term>
sentence
</term>
. This stands
|
#18976
We use a corpus of bracketed sentences, called a Treebank, in combination with decision tree building to tease out the relevant aspects of a parse tree that will determine the correctparse of a sentence. |
other,24-4-H92-1026,bq |
the hope of generating the correct
<term>
|
parse
|
</term>
. In
<term>
head-to-head tests
</term>
|
#19005
This stands in contrast to the usual approach of further grammar tailoring via the usual linguistic introspection in the hope of generating the correctparse. |
other,20-1-H92-1026,bq |
, that takes advantage of detailed
<term>
|
linguistic information
|
</term>
to resolve
<term>
ambiguity
</term>
.
|
#18913
We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailedlinguistic information to resolve ambiguity. |
other,10-4-H92-1026,bq |
contrast to the usual approach of further
<term>
|
grammar
|
</term>
tailoring via the usual
<term>
linguistic
|
#18991
This stands in contrast to the usual approach of furthergrammar tailoring via the usual linguistic introspection in the hope of generating the correct parse. |
measure(ment),1-5-H92-1026,bq |
the correct
<term>
parse
</term>
. In
<term>
|
head-to-head tests
|
</term>
against one of the best existing
|
#19008
Inhead-to-head tests against one of the best existing robust probabilistic parsing models, which we call P-CFG, the HBG model significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error. |
other,2-2-H92-1026,bq |
</term>
.
<term>
HBG
</term>
incorporates
<term>
|
lexical , syntactic , semantic , and structural information
|
</term>
from the
<term>
parse tree
</term>
into
|
#18921
HBG incorporateslexical , syntactic , semantic , and structural information from the parse tree into the disambiguation process in a novel way. |
tech,24-5-H92-1026,bq |
model
</term>
significantly outperforms
<term>
|
P-CFG
|
</term>
, increasing the
<term>
parsing accuracy
|
#19031
In head-to-head tests against one of the best existing robust probabilistic parsing models, which we call P-CFG, the HBG model significantly outperformsP-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error. |
other,24-1-H92-1026,bq |
linguistic information
</term>
to resolve
<term>
|
ambiguity
|
</term>
.
<term>
HBG
</term>
incorporates
<term>
|
#18917
We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolveambiguity. |
tech,10-5-H92-1026,bq |
against one of the best existing robust
<term>
|
probabilistic parsing models
|
</term>
, which we call
<term>
P-CFG
</term>
|
#19017
In head-to-head tests against one of the best existing robustprobabilistic parsing models, which we call P-CFG, the HBG model significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error. |
tech,20-5-H92-1026,bq |
which we call
<term>
P-CFG
</term>
, the
<term>
|
HBG model
|
</term>
significantly outperforms
<term>
P-CFG
|
#19027
In head-to-head tests against one of the best existing robust probabilistic parsing models, which we call P-CFG, theHBG model significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error. |
other,13-2-H92-1026,bq |
structural information
</term>
from the
<term>
|
parse tree
|
</term>
into the
<term>
disambiguation process
|
#18932
HBG incorporates lexical, syntactic, semantic, and structural information from theparse tree into the disambiguation process in a novel way. |
measure(ment),28-5-H92-1026,bq |
<term>
P-CFG
</term>
, increasing the
<term>
|
parsing accuracy
|
</term>
rate from 60 % to 75 % , a 37 % reduction
|
#19035
In head-to-head tests against one of the best existing robust probabilistic parsing models, which we call P-CFG, the HBG model significantly outperforms P-CFG, increasing theparsing accuracy rate from 60% to 75%, a 37% reduction in error. |