#132Several extensions of this basic idea are being discussed and/or evaluated: Similar to activities one can define subsets of larger database and detect those automatically which is shown on a large database of TV shows.
</term>
which all Communicator participants
are
using . In this presentation , we describe
#250To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using.
several field exercises with the Marines and
are
currently developing applications of this
#900We have demonstrated this capability in several field exercises with the Marines and are currently developing applications of this technology in new domains.
#1568Further,in their optimum configuration, bag-of-words methodsare shown to be equivalent to segment order-sensitive methods in terms of retrieval accuracy, but much faster.
also provide evidence that our findings
are
scalable . The theoretical study of the
#1594We also provide evidence that our findings are scalable.
parser
</term>
for a
<term>
language L
</term>
are
directed by a guide which uses the shared
#1712The non-deterministic parsing choices of the main parser for a language Lare directed by a guide which uses the shared derivation forest output by a prior RCL parser for a suitable superset of L .
<term>
wide coverage English grammar
</term>
are
given . While
<term>
paraphrasing
</term>
is
#1751The results of a practical evaluation of this method on a wide coverage English grammarare given.
</term>
improve , even larger improvements
are
possible . We provide a
<term>
logical definition
#1924The value of this approach is that as the operational semantics of natural language applications improve, even larger improvements are possible.
of
<term>
Minimalist grammars
</term>
, that
are
<term>
Stabler 's formalization
</term>
of
<term>
#1937We provide a logical definition of Minimalist grammars, that are Stabler's formalization of Chomsky's minimalist program.
</term>
. These
<term>
models
</term>
, which
are
built from
<term>
shallow linguistic features
#2148These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent a user's informational goals.
linguistic features
</term>
of questions ,
are
employed to predict target variables which
#2157These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent a user's informational goals.
</term>
of
<term>
conversational speech
</term>
are
limited . In this paper , we show how
<term>
#3026Sources of training data suitable for language modeling of conversational speechare limited.
</term>
. The
<term>
units of translation
</term>
are
<term>
blocks
</term>
- pairs of
<term>
phrases
#3422The units of translationare blocks - pairs of phrases.
<term>
training
</term>
, the
<term>
blocks
</term>
are
learned from
<term>
source interval projections
#3450During training, the blocksare learned from source interval projections using an underlying word alignment.
</term>
. Moreover , the
<term>
models
</term>
are
automatically derived by
<term>
decision
#4357Moreover, the modelsare automatically derived by decision tree learning using real dialogue data collected by the system.
</term>
based on the
<term>
user modeling
</term>
are
implemented in Kyoto city bus information
#4389Dialogue strategies based on the user modelingare implemented in Kyoto city bus information system that has been developed at our laboratory.
English-Chinese parallel corpora
</term>
, which
are
then used for disambiguating the
<term>
nouns
#4843In 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.
The backbone of the
<term>
annotation
</term>
are
<term>
semantic roles
</term>
in the
<term>
frame
#4970The backbone of the annotationare semantic roles in the frame semantics paradigm.
summarization
</term>
, where the input documents
are
in Arabic , and the output summary is in
#5190We consider the case of multi-document summarization, where the input documents are in Arabic, and the output summary is in English.
information on how
<term>
human judgments
</term>
are
distributed over the
<term>
text
</term>
.
#5383The paper presents a Bayesian model for text summarization, which explicitly encodes and exploits information on how human judgmentsare distributed over the text.