#365We also report results of a preliminary, qualitative user evaluation of the system, which while broadly positive indicates further work needs to be done on the interface to make users aware of the increased potential of IE-enhanced text browsers.
methods
</term>
. In contrast to previous
work
, we particularly focus on clustering
<term>
#3930In contrast to previous work, we particularly focus on clustering polysemic verbs.
probabilistic context-free grammars
</term>
working
in a ' synchronous ' way . Two
<term>
hardness
#5712These models can be viewed as pairs of probabilistic context-free grammarsworking in a 'synchronous' way.
in the field , which we address with this
work
. Experiments with the
<term>
TREC 2003 and
#5994The lack of automatic methods for scoring system output is an impediment to progress in the field, which we address with this work.
two or more
<term>
verbs
</term>
. Previous
works
on
<term>
shift-reduce dependency parsers
#6651Previous works on shift-reduce dependency parsers may not guarantee the connectivity of a dependency tree due to their weakness at resolving the right-side dependencies.
, will be introduced and used to build a
working
<term>
translation system
</term>
.
<term>
STTK
#6887STTK, a statistical machine translation tool kit, will be introduced and used to build a working translation system.
discussed . In this paper we present our recent
work
on harvesting
<term>
English-Chinese bitexts
#7260In this paper we present our recent work on harvesting English-Chinese bitexts of the laws of Hong Kong from the Web and aligning them to the subparagraph level via utilizing the numbering system in the legal text hierarchy.
empirical MT research
</term>
. This piece of
work
has also laid a foundation for exploring
#7346This piece of work has also laid a foundation for exploring and harvesting English-Chinese bitexts in a larger volume from the Web.
terms of both simplicity and efficiency — to
work
on
<term>
feature selection methods
</term>
#8289We argue that the method is an appealing alternative—in terms of both simplicity and efficiency—to work on feature selection methods within log-linear (maximum-entropy) models.
the
<term>
system 's
</term>
success . This
work
is part of a larger project whose goal
#8738This work is part of a larger project whose goal is to provide sight-impaired users with effective access to information graphics.
downstream modules to process . In previous
work
, we have developed
<term>
hidden Markov
#9450In previous work, we have developed hidden Markov model (HMM) and maximum entropy (Maxent) classifiers that integrate textual and prosodic knowledge sources for detecting sentence boundaries.
with this
<term>
model
</term>
to our prior
work
. We evaluate across two
<term>
corpora
</term>
#9508In this paper, we evaluate the use of a conditional random field (CRF) for this task and relate results with this model to our prior work.
<term>
semantic role labeling
</term>
, previous
work
has largely used independent
<term>
classifiers
#10045Despite much recent progress on accurate semantic role labeling, previous work has largely used independent classifiers, possibly combined with separate label sequence models via Viterbi decoding.
</term>
on
<term>
PropBank
</term>
. Previous
work
has used
<term>
monolingual parallel corpora
#10144Previous work has used monolingual parallel corpora to extract and generate paraphrases.
reasonable success , but they have been shown to
work
well only when there is a good match between
#10438Traditional machine learning techniques have been applied to this problem with reasonable success, but they have been shown to work well only when there is a good match between the training and test data with respect to topic.
describe a
<term>
dialogue system
</term>
that
works
with its
<term>
interlocutor
</term>
to identify
#10625We describe a dialogue system that works with its interlocutor to identify objects.
fundamental problems of
<term>
SMT
</term>
. Our
work
aims at providing useful insights into
#10927Our work aims at providing useful insights into the the computational complexity of those problems.
multiparty dialogue
</term>
. We extend prior
work
in two ways . We first apply approaches
#11420We extend prior work in two ways.
</term>
from the
<term>
contexts
</term>
. It
works
by calculating
<term>
eigenvectors
</term>
#12280It works by calculating eigenvectors of an adjacency graph's Laplacian to recover a submanifold of data from a high dimensionality space and then performing cluster number estimation on the eigenvectors.
an essential underpinning , much recent
work
suggests that
<term>
natural language interfaces
#13492While such decoding is an essential underpinning, much recent work suggests that natural language interfaces will never appear cooperative or graceful unless they also incorporate numerous non-literal aspects of communication, such as robust communication procedures.