#225To 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.
tech,38-1-H01-1017,ak
message-passing infrastructure
</term>
for
<term>
dialogue
systems
</term>
which all Communicator participants
#245To 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.
tech,10-1-H01-1040,ak
from
<term>
information extraction ( IE )
systems
</term>
-
<term>
named entity annotations
</term>
#289In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standard text browser.
tech,30-1-H01-1042,ak
</term>
of
<term>
machine translation ( MT )
systems
</term>
. We believe that these
<term>
evaluation
#579The purpose of this research is to test the efficacy of applying automated evaluation techniques, originally devised for the evaluation of human language learners, to the output of machine translation (MT) systems.
tech,24-2-H01-1042,ak
development of
<term>
machine translation
systems
</term>
. This , the first experiment in
#607We 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.
tech,14-1-H01-1055,ak
the goal of naturally sounding
<term>
dialog
systems
</term>
within reach . However , the improved
#926Recent advances in Automatic Speech Recognition technology have put the goal of naturally sounding dialog systems within reach.
tech,15-2-H01-1055,ak
to light a new problem : as
<term>
dialog
systems
</term>
understand more of what the
<term>
#946However, the improved speech recognition has brought to light a new problem: as dialog systems understand more of what the user tells them, they need to be more sophisticated at responding to the user.
tech,24-3-H01-1055,ak
though rarely in the context of
<term>
dialog
systems
</term>
. We show how research in
<term>
generation
#993The issue of system response to users has been extensively studied by the natural language generation community, though rarely in the context of dialog systems.
tech,10-4-H01-1055,ak
generation
</term>
can be adapted to
<term>
dialog
systems
</term>
, and how the high cost of hand-crafting
#1006We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systems can be overcome by employing machine learning techniques.
tech,20-4-H01-1055,ak
hand-crafting
<term>
knowledge-based generation
systems
</term>
can be overcome by employing
<term>
#1017We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systems can be overcome by employing machine learning techniques.
tech,8-1-H01-1068,ak
evaluation
</term>
of
<term>
spoken dialogue
systems
</term>
. The three tiers measure
<term>
user
#1205We describe a three-tiered approach for evaluation of spoken dialogue systems.
generation of natural language
</term>
, current
systems
use
<term>
manual or semi-automatic methods
#1768While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases.
tech,11-4-P01-1056,ak
performs better than the
<term>
rule-based
systems
</term>
and the
<term>
baselines
</term>
, and
#2112We show that the trainable sentence planner performs better than the rule-based systems and the baselines, and as well as the hand-crafted system.
phrases
</term>
degrades the performance of our
systems
. In this paper , we introduce a
<term>
generative
#2666Learning only syntactically motivated phrases degrades the performance of our systems.
tech,18-2-N03-1018,ak
<term>
output
</term>
of
<term>
black-box OCR
systems
</term>
in order to make it more useful for
#2733The model is designed for use in error correction, with a focus on post-processing the output of black-box OCR systems in order to make it more useful for NLP tasks.
tech,18-3-N03-1026,ak
quality
</term>
of
<term>
sentence condensation
systems
</term>
. An
<term>
experimental evaluation
#2859Furthermore, we propose the use of standard parser evaluation methods for automatically evaluating the summarization quality of sentence condensation systems.
precision
</term>
and
<term>
recall
</term>
on both
systems
. Motivated by these arguments , we introduce
#4091In this paper we formulate story link detection and new event detection as information retrieval task and hypothesize on the impact of precision and recall on both systems.
tech,8-1-P03-1031,ak
understanding process
</term>
in
<term>
spoken dialogue
systems
</term>
. This process enables the
<term>
system
#4137This paper concerns the discourse understanding process in spoken dialogue systems.
tech,15-1-P03-1033,ak
</term>
to each user in
<term>
spoken dialogue
systems
</term>
. Unlike previous studies that focus
#4298We address appropriate user modeling in order to generate cooperative responses to each user in spoken dialogue systems.
tech,6-4-H05-1005,ak
use of multiple
<term>
machine translation
systems
</term>
provides yet more
<term>
redundancy
#5230Further, the use of multiple machine translation systems provides yet more redundancy, yielding different ways to realize that information in English.