#59Traditional information retrieval techniquesuse a histogram of keywords as the document representation but oral communication may offer additional indices such as the time and place of the rejoinder and the attendance.
component performance
</term>
. We describe our
use
of this approach in numerous fielded user
#1226We describe our use of this approach in numerous fielded user studies conducted with the U.S. military.
natural language
</term>
, current systems
use
<term>
manual or semi-automatic methods
</term>
#1769While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases.
</term>
. The
<term>
model
</term>
is designed for
use
in
<term>
error correction
</term>
, with a
#2718The 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.
selection
</term>
. Furthermore , we propose the
use
of standard
<term>
parser evaluation methods
#2844Furthermore, we propose the use of standard parser evaluation methods for automatically evaluating the summarization quality of sentence condensation systems.
the
<term>
system output
</term>
due to the
use
of a
<term>
constraint-based parser/generator
#2904Overall 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.
demonstrates the following ideas : ( i ) explicit
use
of both preceding and following
<term>
tag
#2926We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features.
network representation
</term>
, ( ii ) broad
use
of
<term>
lexical features
</term>
, including
#2944We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features.
multiple consecutive words , ( iii ) effective
use
of
<term>
priors
</term>
in
<term>
conditional
#2961We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features.
<term>
small-sized bilingual corpus
</term>
, we
use
an
<term>
out-of-domain bilingual corpus
</term>
#3097In order to boost the translation quality of EBMT based on a small-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, the language model of an in-domain monolingual corpus.
</term>
. During
<term>
decoding
</term>
, we
use
a
<term>
block unigram model
</term>
and a
<term>
#3433During decoding, we use a block unigram model and a word-based trigram language model.
</term>
. Unlike conventional methods that
use
<term>
hand-crafted rules
</term>
, the proposed
#4240Unlike conventional methods that use hand-crafted rules, the proposed method enables easy design of the discourse understanding process.
the
<term>
segmentation accuracy
</term>
, we
use
an
<term>
unsupervised algorithm
</term>
for
#4715To improve the segmentation accuracy, we use an unsupervised algorithm for automatically acquiring new stems from a 155 million word unsegmented corpus, and re-estimate the model parameters with the expanded vocabulary and training corpus.
for that difference . In this paper , we
use
the
<term>
information redundancy
</term>
in
#5156In this paper, we use the information redundancy in multilingual input to correct errors in machine translation and thus improve the quality of multilingual summaries.
</term>
in the input documents . Further , the
use
of multiple
<term>
machine translation systems
#5225Further, the use of multiple machine translation systems provides yet more redundancy, yielding different ways to realize that information in English.
<term>
reranking approaches
</term>
. We make
use
of a
<term>
conditional log-linear model
</term>
#5447We make use of a conditional log-linear model, with hidden variables representing the assignment of lexical items to word clusters or word senses.
</term>
are described briefly , as well as the
use
of
<term>
ILIMP
</term>
in a modular
<term>
syntactic
#6211Other tasks using the method developed for ILIMP are described briefly, as well as the use of ILIMP in a modular syntactic analysis system.
establishes the equivalence between the standard
use
of
<term>
BLEU
</term>
in
<term>
word n-grams
#6275This study establishes the equivalence between the standard use of BLEU in word n-grams and its application at the character level.
at the
<term>
character level
</term>
. The
use
of
<term>
BLEU
</term>
at the
<term>
character
#6290The use of BLEU at the character level eliminates the word segmentation problem: it makes it possible to directly compare commercial systems outputting unsegmented texts with, for instance, statistical MT systems which usually segment their outputs.
high
<term>
accuracy
</term>
of the model , the
use
of
<term>
smoothing
</term>
in an
<term>
unlexicalized
#8996In addition to the high accuracy of the model, the use of smoothing in an unlexicalized parser allows us to better examine the interplay between smoothing and parsing results.