|
information yet it is also time consuming
|
to
|
document . Given the development of
<term>
|
#14
Oral communication is ubiquitous and carries important information yet it is also time consuming to document. |
|
<term>
scenario templates
</term>
- can be used
|
to
|
enhance access to
<term>
text collections
|
#301
In 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. |
|
Rapid system development
</term>
and porting
|
to
|
new
<term>
domains
</term>
via
<term>
knowledge-based
|
#505
(iii) Rapid system development and porting to new domains via knowledge-based automated acquisition of grammars. |
|
</term>
. The purpose of this research is
|
to
|
test the efficacy of applying
<term>
automated
|
#550
The 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. |
|
can converse with their logistics system
|
to
|
place a supply or information request .
|
#839
Using LCS-Marine, tactical personnel can converse with their logistics system to place a supply or information request. |
|
<term>
speech recognition
</term>
has brought
|
to
|
light a new problem : as
<term>
dialog systems
|
#938
However, 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. |
|
dynamic language model combination
</term>
|
to
|
improve the
<term>
performance
</term>
further
|
#1146
We provide experimental results that clearly show the need for a dynamic language model combinationto improve the performance further. |
|
</term>
applying
<term>
mutual information
</term>
|
to
|
reduce the
<term>
error-correction rules
</term>
|
#1271
The paper also proposes rule-reduction algorithm applying mutual informationto reduce the error-correction rules. |
|
speech acts
</term>
and the decision of how
|
to
|
combine them into one or more
<term>
sentences
|
#1326
Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences. |
|
find that
<term>
indexing
</term>
according
|
to
|
simple
<term>
character bigrams
</term>
produces
|
#1541
Over two distinct datasets, we find that indexing according to simple character bigrams produces a retrieval accuracy superior to any of the tested word N-gram models. |
|
parsing technique
</term>
whose purpose is
|
to
|
improve the practical efficiency of
<term>
|
#1691
In this paper, we study a parsing technique whose purpose is to improve the practical efficiency of RCL parsers. |
|
systems use manual or semi-automatic methods
|
to
|
collect
<term>
paraphrases
</term>
. We present
|
#1773
While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases. |
|
frequently enough in
<term>
dialog
</term>
|
to
|
warrant serious
<term>
attention
</term>
,
|
#1853
These words appear frequently enough in dialogto warrant serious attention, yet present natural language search engines perform poorly on queries containing them. |
|
Our
<term>
logical definition
</term>
leads
|
to
|
a neat relation to
<term>
categorial grammar
|
#1950
Our logical definition leads to a neat relation to categorial grammar, (yielding a treatment of Montague semantics), a parsing-as-deduction in a resource sensitive logic, and a learning algorithm from structured data (based on a typing-algorithm and type-unification). |
|
subjective human judgments
</term>
. In order
|
to
|
perform an exhaustive comparison , we also
|
#2073
In order to perform an exhaustive comparison, we also evaluate a hand-crafted template-based generation component, two rule-based sentence planners, and two baseline sentence planners. |
|
</term>
of
<term>
questions
</term>
, are employed
|
to
|
predict target variables which represent
|
#2158
These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent a user's informational goals. |
|
with off-the-shelf
<term>
classifiers
</term>
|
to
|
give
<term>
utterance classification performance
|
#2233
The method combines domain independent acoustic models with off-the-shelf classifiersto give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription. |
tech,21-1-N03-1004,bq |
multi-strategy and multi-source approach
|
to
|
question answering
</term>
which is based
|
#2331
Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from different answering agents searching for answers in multiple corpora. |
|
</term>
. We apply our
<term>
system
</term>
|
to
|
the task of
<term>
scoring
</term>
alternative
|
#2460
We apply our systemto the task of scoring alternative speech recognition hypotheses (SRH) in terms of their semantic coherence. |
|
decoding algorithm
</term>
that enables us
|
to
|
evaluate and compare several , previously
|
#2552
We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. |