H92-1099 |
improving recognition results . Extend
|
parse scoring
|
algorithm to include prominence
|
P13-2019 |
baseline model , the only change is
|
parse scoring
|
. By running a complete inference
|
W03-0402 |
x ) ) = 12PrX ( x ) . For any
|
parse scoring
|
function f , let gf ( x1 , x2
|
W15-2208 |
rules . The new rules enable the
|
parse scoring
|
function to incorporate the syntactic
|
W03-0402 |
10 ) 0 otherwise where f is a
|
parse scoring
|
function . Let E = { ( x , ¯
|
H92-1099 |
prediction algorithms . Utilize the
|
parse scoring
|
algorithm in speech under - standing
|
W15-2208 |
conjuncts can be incorporated to the
|
parse scoring
|
function . Although we are yet
|
H93-1025 |
dependencies , punctuation , and
|
parse scoring
|
. Nevertheless , for all of these
|
H93-1025 |
ambiguity resolution - the SG
|
parse scoring
|
system . This scoring system
|
H94-1091 |
marcher output . * Improve the
|
parse scoring
|
algorithm performance by exploring
|
H91-1082 |
read speech . * Implement the
|
parse scoring
|
algorithm using automatically
|
H91-1082 |
additional data . * Utilize the
|
parse scoring
|
algorithm in speech under - standing
|
H92-1099 |
previous work in analysis/synthesis
|
parse scoring
|
by introducing a new probabilistic
|
H92-1087 |
thought . <title> Probabilistic
|
Parse Scoring
|
Based on Prosodic Phrasing </title>
|
H93-1025 |
or-slots " , punctuation , and
|
parse scoring
|
. All these rule types make use
|
H93-1082 |
in this domain . * Improve the
|
parse scoring
|
algorithm performance in the
|
C88-1040 |
aggregations makes up a complete
|
parse scoring
|
6 ( Jonclnsmns and links with
|