#824We have built and will demonstrate an application of this approach called LCS-Marine.
confidence
</term>
. We describe a three-tiered
approach
for
<term>
evaluation
</term>
of
<term>
spoken
#1199We describe a three-tiered approach for evaluation of spoken dialogue systems.
performance
</term>
. We describe our use of this
approach
in numerous fielded user studies conducted
#1229We describe our use of this approach in numerous fielded user studies conducted with the U.S. military.
military . This paper proposes a practical
approach
employing
<term>
n-gram models
</term>
and
<term>
#1246This paper proposes a practical approach employing n-gram models and error-correction rules for Thai key prediction and Thai-English language identification.
of the same
<term>
source text
</term>
. Our
approach
yields
<term>
phrasal and single word lexical
#1802Our approach yields phrasal and single word lexical paraphrases as well as syntactic paraphrases.
operational semantics
</term>
. The value of this
approach
is that as the
<term>
operational semantics
#1908The value of this approach is that as the operational semantics of natural language applications improve, even larger improvements are possible.
tech,32-1-P01-1056,ak
hand-crafted template-based or rule-based
approaches
</term>
. In this paper We experimentally
#2049Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced with trainable components can compete with hand-crafted template-based or rule-based approaches.
developed a multi-strategy and multi-source
approach
to
<term>
question answering
</term>
which
#2331Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from different answering agents searching for answers in multiple corpora.
tech,2-1-N03-2025,ak
quality
</term>
. A novel
<term>
bootstrapping
approach
</term>
to
<term>
Named Entity ( NE ) tagging
#3289A novel bootstrapping approach to Named Entity (NE) tagging using concept-based seeds and successive learners is presented.
successive learners
</term>
is presented . This
approach
only requires a few common
<term>
noun or
#3307This approach only requires a few common noun or pronoun seeds that correspond to the concept for the targeted NE, e.g. he/she/man/woman for PERSON NE.
</term>
. The resulting
<term>
NE system
</term>
approaches
<term>
supervised NE performance
</term>
for
#3381The resulting NE systemapproaches supervised NE performance for some NE types.
tech,0-4-N03-3010,ak
robustness and flexibility .
<term>
Statistical
approach
</term>
is much more robust but less accurate
#3536Statistical approach is much more robust but less accurate.
<term>
corpus data
</term>
. We describe a new
approach
which involves clustering
<term>
subcategorization
#3907We describe a new approach which involves clustering subcategorization frame (SCF) distributions using the Information Bottleneck and nearest neighbour methods.
tech,3-1-P03-1022,ak
</term>
. We apply a
<term>
decision tree based
approach
</term>
to
<term>
pronoun resolution
</term>
#3980We apply a decision tree based approach to pronoun resolution in spoken dialogue.
tech,4-1-P03-1050,ak
paper presents an
<term>
unsupervised learning
approach
</term>
to building a
<term>
non-English (
#4438This paper presents an unsupervised learning approach to building a non-English (Arabic) stemmer.
be given for
<term>
Arabic
</term>
, but the
approach
is applicable to any
<term>
language
</term>
#4523Examples and results will be given for Arabic, but the approach is applicable to any language that needs affix removal.
tech,1-6-P03-1050,ak
removal
</term>
. Our
<term>
resource-frugal
approach
</term>
results in 87.5 %
<term>
agreement
</term>
#4536Our resource-frugal approach results in 87.5% agreement with a state of the art, proprietary Arabic stemmer built using rules, affix lists, and human annotated text, in addition to an unsupervised component.
learning
</term>
. In this paper , we evaluate an
approach
to automatically acquire
<term>
sense-tagged
#4830In this paper, we evaluate an approach to automatically acquire sense-tagged training data from English-Chinese parallel corpora, which are then used for disambiguating the nouns in the SENSEVAL-2 English lexical sample task.
accuracy difference
</term>
between the two
approaches
is only 14.0 % , and the difference could
#4887On a subset of the most difficult SENSEVAL-2 nouns, the accuracy difference between the two approaches is only 14.0%, and the difference could narrow further to 6.5% if we disregard the advantage that manually sense-tagged data have in their sense coverage.
tech,5-3-H05-1032,ak
</term>
. It is found that the
<term>
Bayesian
approach
</term>
generally leverages performance of
#5411It is found that the Bayesian approach generally leverages performance of a summarizer, at times giving it a significant lead over non-Bayesian models.