... Learning Noun Phrase Anaphoricity to Improve Coreference Resolution:
Issues in Representation and Optimization
Vincent Ng
Department of Computer Science
Cornell ... paper is to improve learning-
based coreference systems using automatically
computed anaphoricity information. In particular,
we examine two important, yet largely unexplored,
issues in anaphor...
... adding
gold-standard bracketing within each
noun phrase in the Penn Treebank. We
then examine the consistency and reliabil-
ity of our annotations. Finally, we use
this resource to determine ... gold-standard labelled
bracketing for every ambiguous noun phrase in the
Penn Treebank. We describe the annotation guide-
lines and process, including the use of named en-
tity data...
... determine that “Mr. Clinton” and
“Clinton” are coreferent using string-matching
features, and that “Clinton” and “she” are coref-
erent based on proximity and lack of evidence for
gender and number ... Learning noun phrase anaphoricity
to improve conference resolution: Issues in repre-
sentation and optimization. In Proceedings of the
42nd Annual Meeting of the A...
... method of as-
signing supertags. Instead, conjuncts are identified
during the head-finding stage, and then assigned the
supertag dominating the entire coordination. Inter-
vening non-conjunct nodes ... combined using combinatory rules
such as forward and backward application:
X /Y Y ⇒ X (>) (1)
Y X \Y ⇒ X (<) (2)
Other rules such as composition and type-raising are
used to analyse...
... head words and begins by looking at how the
different handling of coordination in noun phrases
and base noun phrases (NPB) affects coordination
disambiguation.
1
We look at how we might improve
the ... in the phrase are nominal.
However, we found that out of 1,417 examples
of NP coordination in sections 02 to 21, involving
phrases containing only nouns (common nouns or a
m...
... taking the average of 4 ques-
tions)
3
to the number of items presented (DB) for
each modality, using curve fitting. In contrast to
linear regression, curve fitting does not assume a
linear inductive ... presentation. We partition
the database feature into 3 bins, taking the first in-
tersection point between verbal and multimodal re-
ward and the turning point of the multimodal func...
... found
in the page for the sense being trained.
• TiMBL-inlinks uses the examples found in
Wikipedia pages pointing to the sense being
trained.
• TiMBL-all uses both sources of examples.
In order to ... H. Roitman, and N. Zwerdling. 2009. En-
hancing Cluster Labeling using Wikipedia. In Pro-
ceedings of the 32nd international ACM SIGIR con-
ference on Research and development...
... cross-entity inference for event extraction (including training and testing processes)
In the training process, for every entity type in
the ACE training corpus, a clustering technique
(CLUTO toolkit)
3
... extraction. In
Proc. COLING/ACL 2006 Workshop on Annotating
and Reasoning about Time and Events.Sydney, Aus-
tralia.
Jenny Rose Finkel, Trond Grenager and Christopher
M...
... Chinese in-
put system is phonetic and pinyin based ap-
proach, because Chinese people are taught to
write phonetic and pinyin syllables of each Chi-
nese character in primary school.
In Chinese, ... systems.
In our previous work (Tsai, 2005), a word-
pair (WP) identifier was proposed and shown a
simple and effective way to improve Chinese
input systems by providing t...
... experimented with both
ways of defining the history and have not observed
any benefit of sequential learning techniques by
defining the history for sequential learning in terms
of previous messages. ... style interactions. The goal of assess-
ing the quality of interactions in that context is to
enable the quality and nature of discussions that
occur within an on-line discussi...