|
for use in
<term>
error correction
</term>
,
|
with
|
a focus on
<term>
post-processing
</term>
the
|
#2722
The model is designed for use in error correction, with a focus on post-processing the output of black-box OCR systems in order to make it more useful for NLP tasks. |
|
</term>
on standard
<term>
WSD datasets
</term>
,
|
with
|
promising results . This paper presents
|
#7017
We evaluated the topic signatures on a WSD task, where we trained a second-order vector co-occurrence algorithm on standard WSD datasets, with promising results. |
|
relies upon the
<term>
actor paradigm
</term>
,
|
with
|
<term>
concurrency
</term>
entering through
|
#21050
The computation model relies upon the actor paradigm, with concurrency entering through asynchronous message passing between actors. |
|
</term>
for each input
<term>
sentence
</term>
,
|
with
|
associated
<term>
probabilities
</term>
that
|
#8677
The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of these parses. |
|
<term>
system
</term>
is state-of-the-art ,
|
with
|
guaranteed
<term>
grammaticality
</term>
of
|
#2893
Overall summarization quality of the proposed system is state-of-the-art, with guaranteed grammaticality of the system output due to the use of a constraint-based parser/generator. |
|
</term>
( that of
<term>
Collins [ 1999 ]
</term>
)
|
with
|
evidence from an additional 500,000
<term>
|
#8816
The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the original model. |
|
classification ( maximum entropy )
</term>
|
with
|
<term>
linguistic information
</term>
. Instead
|
#6005
In this paper, we present a corpus-based supervised word sense disambiguation (WSD) system for Dutch which combines statistical classification (maximum entropy)with linguistic information. |
|
improvement in
<term>
recognition accuracy
</term>
|
with
|
the
<term>
mixture trigram models
</term>
as
|
#21278
Using the BU recognition system, experiments show a 7% improvement in recognition accuracywith the mixture trigram models as compared to using a trigram model. |
|
progress in the field , which we address
|
with
|
this work . Experiments with the
<term>
TREC
|
#7591
The lack of automatic methods for scoring system output is an impediment to progress in the field, which we address with this work. |
|
</term>
results in 87.5 %
<term>
agreement
</term>
|
with
|
a state of the art , proprietary
<term>
Arabic
|
#4540
Our resource-frugal approach results in 87.5% agreementwith a state of the art, proprietary Arabic stemmer built using rules, affix lists, and human annotated text, in addition to an unsupervised component. |
|
. The results of this experiment , along
|
with
|
a preliminary analysis of the factors involved
|
#762
The results of this experiment, along with a preliminary analysis of the factors involved in the decision making process will be presented here. |
|
language definition
</term>
are presented , along
|
with
|
a
<term>
control structure
</term>
for an
<term>
|
#13415
Representative samples from an entity-oriented language definition are presented, along with a control structure for an entity-oriented parser, some parsing strategies that use the control structure, and worked examples of parses. |
|
class
<term>
NP
</term>
are reported , along
|
with
|
an
<term>
exponential time lower-bound
</term>
|
#7487
Two hardness results for the class NP are reported, along with an exponential time lower-bound for certain classes of algorithms that are currently used in the literature. |
|
tracking algorithm
</term>
is presented along
|
with
|
a description of its
<term>
implementation
|
#14048
A dialogue acquisition and tracking algorithm is presented along with a description of its implementation in a voice interactive system. |
|
</term>
. Thus , our method can be applied
|
with
|
great benefit to
<term>
language pairs
</term>
|
#9107
Thus, our method can be applied with great benefit to language pairs for which only scarce resources are available. |
|
<term>
planning-based architecture
</term>
|
with
|
a variety of
<term>
language processing modules
|
#3644
The JAVELIN system integrates a flexible, planning-based architecturewith a variety of language processing modules to provide an open-domain question answering capability on free text. |
|
the operation of the mechanisms associated
|
with
|
<term>
attentional state
</term>
. This processing
|
#14364
Discourse processing requires recognizing how the utterances of the discourse aggregate into segments, recognizing the intentions expressed in the discourse and the relationships among intentions, and tracking the discourse through the operation of the mechanisms associated with attentional state. |
|
log ( d ) overheads
</term>
often associated
|
with
|
<term>
structure-sharing of graphs
</term>
|
#18001
We propose a method of attaining such a design through a method of structure-sharing which avoids log(d) overheads often associated with structure-sharing of graphs without any use of costly dependency pointers. |
|
<term>
computational problems
</term>
associated
|
with
|
<term>
probabilistic translation models
</term>
|
#7441
This paper investigates some computational problems associated with probabilistic translation models that have recently been adopted in the literature on machine translation. |
|
</term>
in such
<term>
systems
</term>
. It begins
|
with
|
a characterization of what a
<term>
user
|
#16051
It begins with a characterization of what a user model is and how it can be used. |