S15-1035 |
discourse deixis engine on top of
|
NP coreference resolution
|
. 2 Related Work Coreference
|
J08-3002 |
systems on the non-pronominal
|
NP coreference resolution
|
. We used as the baseline the
|
W06-0302 |
differs from traditional supervised
|
NP coreference resolution
|
in two important aspects . First
|
P09-1074 |
performance results reported for
|
NP coreference resolution
|
. For our investigations , we
|
P09-1074 |
studies complexity issues for
|
NP coreference resolution
|
using a " good " , i.e. near
|
P09-1074 |
examine the state-of-the-art in
|
NP coreference resolution
|
. We show the relative impact
|
W06-1640 |
resolution task can benefit from
|
NP coreference resolution
|
training data from a different
|
S15-1035 |
is independent from the NP --
|
NP coreference resolution
|
component : competition between
|
P09-1074 |
statements about the state-of-theart in
|
NP coreference resolution
|
. In particular , it remains
|
W97-1309 |
extremely low compared to the
|
NP coreference resolution
|
result 65 because in the case
|
P04-1017 |
The module is a duplicate of the
|
NP coreference resolution
|
system by Soon et al. ( 2001
|
W12-2501 |
2010 ) . The task of automatic
|
NP coreference resolution
|
is to determine " which NPs in
|
C04-1033 |
string-matching is a crucial factor for
|
NP coreference resolution
|
. As shown in the flgure , the
|
W15-1503 |
involved anaphora resolution and
|
NP coreference resolution
|
( Or˘asan et al. , 2008
|
P02-1014 |
Lappin and Leass ( 1994 ) ) and
|
NP coreference resolution
|
( e.g. Grishman ( 1995 ) , Lin
|
P09-1074 |
light on the state-of-the-art in
|
NP coreference resolution
|
by teasing apart the differences
|
S15-1035 |
impact of our system on top of an
|
NP coreference resolution
|
engine , we consider the following
|
W06-0106 |
U.S. president Bill Clinton .
|
NP coreference resolution
|
is an important subtask in natural
|