#4Oral communication is ubiquitous and carries important information yet it is also time consuming to document.
. Given the development of storage media
and
networks one could just record and store
#23Given the development of storage media and networks one could just record and store a conversation for documentation.
media and networks one could just record
and
store a conversation for documentation
#29Given the development of storage media and networks one could just record and store a conversation for documentation.
additional
<term>
indices
</term>
such as the time
and
place of the rejoinder and the attendance
#79Traditional information retrieval techniques use 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.
such as the time and place of the rejoinder
and
the attendance . An alternative
<term>
index
#84Traditional information retrieval techniques use 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.
of those activities in meeting situation
and
everyday rejoinders . Several extensions
#122This paper addresses the problem of the automatic detection of those activities in meeting situation and everyday rejoinders.
subsets
</term>
of larger
<term>
database
</term>
and
detect those automatically which is shown
#148Several extensions of this basic idea are being discussed and/or evaluated: Similar to activities one can define subsets of larger databaseand detect those automatically which is shown on a large database of TV shows.
a large database of TV shows . Emotions
and
other
<term>
indices
</term>
such as the dominance
#164Emotions and other indices such as the dominance distribution of speakers might be available on the surface and could be used directly.
speakers might be available on the surface
and
could be used directly . Despite the small
#180Emotions and other indices such as the dominance distribution of speakers might be available on the surface and could be used directly.
presentation , we describe the features of
and
requirements for a genuinely useful
<term>
#262In this presentation, we describe the features of and requirements for a genuinely useful software infrastructure for this purpose.
</term>
-
<term>
named entity annotations
</term>
and
<term>
scenario templates
</term>
- can be
#294In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotationsand scenario templates - can be used to enhance access to text collections via a standard text browser.
tech,11-2-H01-1041,ak
modules
</term>
,
<term>
language understanding
and
generation modules
</term>
mediated by a
<term>
#424The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame.
relatively
<term>
free word order
</term>
,
and
frequent omissions of
<term>
arguments
</term>
#470The key features of the system include: (i) Robust efficient parsing of Korean (a verb final language with overt case markers, relatively free word order, and frequent omissions of arguments).
via
<term>
word sense disambiguation
</term>
and
accurate
<term>
word order generation
</term>
#487(ii) High quality translation via word sense disambiguationand accurate word order generation of the target language.
iii ) Rapid
<term>
system development
</term>
and
<term>
porting to new domains
</term>
via
<term>
#503(iii) Rapid system developmentand porting to new domains via knowledge-based automated acquisition of grammars.
Korean newspaper articles
</term>
on missiles
and
chemical biological warfare , the
<term>
#524Having been trained on Korean newspaper articles on missiles and chemical biological warfare, the system produces the translation output sufficient for content understanding of the original document.
</term>
, the
<term>
translation process
</term>
and
the development of
<term>
machine translation
#601We believe that these evaluation techniques will provide information about both the human language learning process, the translation processand the development of machine translation systems.
</term>
that mediate between
<term>
users
</term>
and
<term>
information sources
</term>
. We have
#810We integrate a spoken language understanding system with intelligent mobile agents that mediate between usersand information sources.
information sources
</term>
. We have built
and
will demonstrate an application of this
#817We have built and will demonstrate an application of this approach called LCS-Marine.
several field exercises with the Marines
and
are currently developing applications of
#899We have demonstrated this capability in several field exercises with the Marines and are currently developing applications of this technology in new domains.