<term>
users
</term>
and
<term>
information sources
#808We integrate a spoken language understanding system with intelligent mobile agents that mediate between users and information sources.
annotators
</term>
can reliably differentiate
between
semantically coherent and incoherent
<term>
#2493We conducted an annotation experiment and showed that human annotators can reliably differentiate between semantically coherent and incoherent speech recognition hypotheses.
quality
</term>
shows a close correlation
between
the
<term>
automatic parse-based evaluation
#2871An experimental evaluation of summarization quality shows a close correlation between the automatic parse-based evaluation and a manual evaluation of generated strings.
Those
<term>
hubs
</term>
mark the boundary
between
<term>
root
</term>
and
<term>
suffix
</term>
,
#3214Those hubs mark the boundary between root and suffix, achieving similar performance to more complex mixtures of techniques.
</term>
, the
<term>
accuracy difference
</term>
between
the two approaches is only 14.0 % , and
#4884On a subset of the most difficult SENSEVAL-2 nouns, the accuracy differencebetween 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.
tool is therefore designed to distinguish
between
the
<term>
anaphoric occurrences
</term>
of
#6137This tool is therefore designed to distinguish between the anaphoric occurrences of il, for which an anaphora resolution system has to look for an antecedent, and the expletive occurrences of this pronoun, for which it does not make sense to look for an antecedent.
. This study establishes the equivalence
between
the standard use of
<term>
BLEU
</term>
in
<term>
#6272This study establishes the equivalence between the standard use of BLEU in word n-grams and its application at the character level.
research area as well as the relationship
between
research organizations and research areas
#6581We determined the changes in the number of papers published for each research organization and on each research area as well as the relationship between research organizations and research areas.
wordnets
</term>
built upon correspondences
between
different
<term>
languages
</term>
can play
#7060Parallel wordnets built upon correspondences between different languages can play a crucial role in multilingual knowledge processing.
Since there is no
<term>
homomorphism
</term>
between
pairs of
<term>
monolingual wordnets
</term>
#7078Since there is no homomorphismbetween pairs of monolingual wordnets, we must rely on lexical semantic relation (LSR) mappings to ensure conceptual cohesion.
there is not a large performance difference
between
the two
<term>
models
</term>
. The results
#7769Experimental results showed that the proposed method achieves almost 60% accuracy and that there is not a large performance difference between the two models.
allows us to better examine the interplay
between
<term>
smoothing
</term>
and parsing results
#9010In 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.
Extracting
<term>
semantic relationships
</term>
between
<term>
entities
</term>
is challenging . This
#9268Extracting semantic relationshipsbetween entities is challenging.
structure , with strong
<term>
dependencies
</term>
between
<term>
arguments
</term>
. We show how to build
#10085This stands in stark contrast to the linguistic observation that a core argument frame is a joint structure, with strong dependenciesbetween arguments.
work well only when there is a good match
between
the
<term>
training and test data
</term>
with
#10447Traditional 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.
of reference
</term>
, and flexible links
between
<term>
semantics
</term>
and
<term>
collaborative
#10658Our contributions include a concise, modular architecture with reversible processes of understanding and generation, an information-state model of reference, and flexible links between semantics and collaborative problem solving.
demonstrate an additional increase of correlation
between
<term>
automatic evaluation measures
</term>
#11391Results from experiments with word dependent substitution costs will demonstrate an additional increase of correlation between automatic evaluation measures and human judgment.
research context to uncover relationships
between
<term>
language
</term>
and behavioral patterns
#11851As evidence of its usefulness and usability, it has been used successfully in a research context to uncover relationships between language and behavioral patterns in two distinct domains: tutorial dialogue (Kumar et al., submitted) and on-line communities (Arguello et al., 2006).
disambiguate various
<term>
relations
</term>
between
<term>
named entities
</term>
by use of various
#12264This paper presents an unsupervised learning approach to disambiguate various relationsbetween named entities by use of various lexical and syntactic features from the contexts.
examines what kind of
<term>
similarity
</term>
between
<term>
words
</term>
can be represented by
#12414This paper examines what kind of similaritybetween words can be represented by what kind of word vectors in the vector space model.