A00-2003 |
describe a supervised probabilistic
|
pronoun resolution
|
algorithm which is based on complete
|
A92-1028 |
in the algorithm . <title> Zero
|
Pronoun Resolution
|
in a Japanese to English Machine
|
C00-1045 |
have mostly been applied to the
|
pronoun resolution
|
problem . In the following we
|
C04-1050 |
. Section 3 outlines our zero
|
pronoun resolution
|
system . Section 4 describes
|
C00-2133 |
on accented demonstratives and
|
pronoun resolution
|
is extremely scarce . Pioneering
|
C04-1050 |
its incorporation into our zero
|
pronoun resolution
|
system . The word sense disambiguation
|
A92-1028 |
mentioned here , an example of zero
|
pronoun resolution
|
is given in ( 7 ) . * The arrows
|
C04-1050 |
conducted experiments of zero
|
pronoun resolution
|
on two different domain corpora
|
C02-1078 |
compute the probability for zero
|
pronoun resolution
|
. We varied a threshold for the
|
C04-1050 |
<title> Improving Japanese Zero
|
Pronoun Resolution
|
by Global Word Sense Disambiguation
|
C00-2133 |
prominence is to be useful for
|
pronoun resolution
|
, then there must be prosodic
|
A00-2003 |
speech pose problems for both
|
pronoun resolution
|
and generation because of the
|
C02-2023 |
algorithms such as inference and
|
pronoun resolution
|
, as well as inclusion of additional
|
C02-1078 |
literature associated with zero
|
pronoun resolution
|
and our preliminary study , we
|
C02-1078 |
further explored . Third , in a zero
|
pronoun resolution
|
( i.e. , antecedent identification
|
C04-1050 |
sense disambiguation into our zero
|
pronoun resolution
|
system , and conducted experiments
|
C02-1027 |
Bulgarian of Mitkovs knowledge-poor
|
pronoun resolution
|
approach ( Mitkov , 1998 ) .
|
C00-2133 |
shown them to be imporlant for
|
pronoun resolution
|
. Features illclude attributes
|
C02-1078 |
two-fold : we evaluated only zero
|
pronoun resolution
|
( an - tecedent identification
|
C00-2133 |
Are Acoustic Features Useful for
|
Pronoun Resolution
|
? The answer is : probably not
|