participants are using . In this presentation , we
describe
the features of and requirements for a
#258In this presentation, we describe the features of and requirements for a genuinely useful software infrastructure for this purpose.
a standard
<term>
text browser
</term>
. We
describe
how this information is used in a
<term>
#314We describe how this information is used in a prototype system designed to support information workers' access to a pharmaceutical news archive as part of their industry watch function.
with the best
<term>
confidence
</term>
. We
describe
a three-tiered approach for
<term>
evaluation
#1196We describe a three-tiered approach for evaluation of spoken dialogue systems.
and
<term>
component performance
</term>
. We
describe
our use of this approach in numerous fielded
#1224We describe our use of this approach in numerous fielded user studies conducted with the U.S. military.
the
<term>
hand-crafted system
</term>
. We
describe
a set of
<term>
supervised machine learning
#2126We describe a set of supervised machine learning experiments centering on the construction of statistical models of WH-questions.
among the target variables . This paper
describes
a method for
<term>
utterance classification
#2208This paper describes a method for utterance classification that does not require manual transcription of training data.
character recognition ( OCR ) model
</term>
that
describes
an end-to-end process in the
<term>
noisy
#2685In this paper, we introduce a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process in the noisy channel framework, progressing from generation of true text through its transformation into the noisy output of an OCR system.
using the
<term>
language model
</term>
. We
describe
a simple
<term>
unsupervised technique
</term>
#3155We describe a simple unsupervised technique for learning morphology by identifying hubs in an automaton.
<term>
NE types
</term>
. In this paper , we
describe
a
<term>
phrase-based unigram model
</term>
#3395In this paper, we describe a phrase-based unigram model for statistical machine translation that uses a much simpler set of model parameters than similar phrase-based models.
undisambiguated
<term>
corpus data
</term>
. We
describe
a new approach which involves clustering
#3904We describe a new approach which involves clustering subcategorization frame (SCF) distributions using the Information Bottleneck and nearest neighbour methods.
evaluating
<term>
WSD programs
</term>
. We
describe
the ongoing construction of a
<term>
large
#4935We describe the ongoing construction of a large, semantically annotated corpus resource as reliable basis for the large-scale acquisition of word-semantic information, e.g. the construction of domain-independent lexica.
over
<term>
non-Bayesian models
</term>
. We
describe
a new method for the representation of
#5431We describe a new method for the representation of NLP structures within reranking approaches.
focused on
<term>
parsing
</term>
, the techniques
described
generalize naturally to NLP structures
#5570Although our experiments are focused on parsing, the techniques described generalize naturally to NLP structures other than parse trees.
retrieval
</term>
from complex news articles
describing
multi-event stories published over time
#5761We consider the problem of question-focused sentence retrieval from complex news articles describing multi-event stories published over time.
direct application of existing metrics . We
describe
a
<term>
method for identifying systematic
#6030We describe a method for identifying systematic patterns in translation data using part-of-speech tag sequences.
method developed for
<term>
ILIMP
</term>
are
described
briefly , as well as the use of
<term>
ILIMP
#6204Other tasks using the method developed for ILIMP are described briefly, as well as the use of ILIMP in a modular syntactic analysis system.
million
<term>
words
</term>
. In this paper , we
describe
<term>
data collection
</term>
,
<term>
transcription
#7229In this paper, we describe data collection, transcription, word segmentation, and part-of-speech annotation of this corpus.
<term>
corpus-based investigations
</term>
are
described
. Moreover , some examples are given that
#7823After a thorough description of the phenomena, the results of corpus-based investigations are described.
boosting approach to ranking problems
</term>
described
in Freund et al. ( 1998 ) . We apply the
#8142We introduce a new method for the reranking task, based on the boosting approach to ranking problemsdescribed in Freund et al. (1998).
</term>
is NP-hard , several approximations are
described
and empirically compared . In experiments
#8543Because exact parsing with a PCFG-LA is NP-hard, several approximations are described and empirically compared.