#7Oral communication is ubiquitous and carries important information yet it is also time consuming to document.
question is , however , how an interesting
information
piece would be found in a
<term>
large database
#45The question is, however, how an interesting information piece would be found in a large database.
tech,1-4-H01-1001,ak
large database
</term>
. Traditional
<term>
information
retrieval techniques
</term>
use a
<term>
histogram
#56Traditionalinformation 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.
tech,10-1-H01-1040,ak
show how two standard outputs from
<term>
information
extraction ( IE ) systems
</term>
-
<term>
#284In this paper we show how two standard outputs frominformation extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standard text browser.
text browser
</term>
. We describe how this
information
is used in a
<term>
prototype system
</term>
#317We 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.
other,14-2-H01-1040,ak
prototype system
</term>
designed to support
<term>
information
workers '
</term>
access to a
<term>
pharmaceutical
#327We describe how this information is used in a prototype system designed to supportinformation workers' access to a pharmaceutical news archive as part of their industry watch function.
evaluation techniques
</term>
will provide
information
about both the
<term>
human language learning
#589We believe that these evaluation techniques will provide information about both the human language learning process, the translation process and the development of machine translation systems.
other,16-2-H01-1049,ak
mediate between
<term>
users
</term>
and
<term>
information
sources
</term>
. We have built and will
#811We integrate a spoken language understanding system with intelligent mobile agents that mediate between users andinformation sources.
other,14-4-H01-1049,ak
logistics system to place a
<term>
supply or
information
request
</term>
. The
<term>
request
</term>
#844Using LCS-Marine, tactical personnel can converse with their logistics system to place a supply or information request.
#1270The paper also proposes rule-reduction algorithm applying mutual information to reduce the error-correction rules.
analyst write a topical report , culling
information
from a large inflow of multilingual , multimedia
#3594The TAP-XL Automated Analyst's Assistant is an application designed to help an English-speaking analyst write a topical report, culling information from a large inflow of multilingual, multimedia data.
tech,16-2-P03-1009,ak
SCF ) distributions
</term>
using the
<term>
Information
Bottleneck and nearest neighbour methods
#3919We describe a new approach which involves clustering subcategorization frame (SCF) distributions using theInformation Bottleneck and nearest neighbour methods.
tech,13-2-P03-1030,ak
<term>
new event detection
</term>
as
<term>
information
retrieval task
</term>
and hypothesize on
#4077In this paper we formulate story link detection and new event detection asinformation retrieval task and hypothesize on the impact of precision and recall on both systems.
other,11-5-P03-1031,ak
ambiguity
</term>
based on
<term>
statistical
information
</term>
obtained from
<term>
dialogue corpora
#4230This paper proposes a method for resolving this ambiguity based on statistical information obtained from dialogue corpora.
</term>
are implemented in Kyoto city bus
information
system that has been developed at our laboratory
#4395Dialogue strategies based on the user modeling are implemented in Kyoto city bus information system that has been developed at our laboratory.
tech,3-7-P03-1050,ak
Task-based evaluation
</term>
using
<term>
Arabic
information
retrieval
</term>
indicates an improvement
#4575Task-based evaluation using Arabic information retrieval indicates an improvement of 22-38% in average precision over unstemmed text, and 96% of the performance of the proprietary stemmer above.
tech,18-1-P03-1068,ak
large-scale acquisition of word-semantic
information
</term>
, e.g. the construction of
<term>
domain-independent
#4956We 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.
other,7-1-H05-1005,ak
difference . In this paper , we use the
<term>
information
redundancy
</term>
in multilingual input
#5158In this paper, we use theinformation redundancy in multilingual input to correct errors in machine translation and thus improve the quality of multilingual summaries.
output summary is in English . Typically ,
information
that makes it to a summary appears in many
#5204Typically, information that makes it to a summary appears in many different lexical-syntactic forms in the input documents.
yielding different ways to realize that
information
in English . We demonstrate how
<term>
errors
#5242Further, the use of multiple machine translation systems provides yet more redundancy, yielding different ways to realize that information in English.