|
database
</term>
and detect those automatically
|
which
|
is shown on a large
<term>
database
</term>
|
#152
Several 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. |
|
mixed-initiative speech dialogue interactions
</term>
|
which
|
reach beyond current capabilities in
<term>
|
#218
To support engaging human users in robust, mixed-initiative speech dialogue interactionswhich 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. |
|
infrastructure
</term>
for
<term>
dialogue systems
</term>
|
which
|
all
<term>
Communicator
</term>
participants
|
#246
To 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 systemswhich all Communicator participants are using. |
|
evaluation
</term>
of the
<term>
system
</term>
,
|
which
|
while broadly positive indicates further
|
#359
We also report results of a preliminary, qualitative user evaluation of the system, which while broadly positive indicates further work needs to be done on the interface to make users aware of the increased potential of IE-enhanced text browsers. |
|
Even more illuminating was the factors on
|
which
|
the
<term>
assessors
</term>
made their decisions
|
#655
Even more illuminating was the factors on which the assessors made their decisions. |
|
were asked to mark the
<term>
word
</term>
at
|
which
|
they made this decision . The results of
|
#749
Additionally, they were asked to mark the word at which they made this decision. |
|
inter-related but distinct tasks , one of
|
which
|
is
<term>
sentence scoping
</term>
, i.e. the
|
#1306
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. |
|
</term>
has revealed many attractive properties
|
which
|
may be used in
<term>
NLP
</term>
. In particular
|
#1614
The theoretical study of the range concatenation grammar [RCG] formalism has revealed many attractive properties which may be used in NLP. |
|
</term>
are directed by a
<term>
guide
</term>
|
which
|
uses the
<term>
shared derivation forest
</term>
|
#1717
The non-deterministic parsing choices of the main parser for a language L are directed by a guidewhich uses the shared derivation forest output by a prior RCL parser for a suitable superset of L. |
|
</term>
called
<term>
alternative markers
</term>
,
|
which
|
includes
<term>
other ( than )
</term>
,
<term>
|
#1831
This paper presents a formal analysis for a large class of words called alternative markers, which includes other (than), such (as), and besides. |
|
connection to
<term>
Montague semantics
</term>
|
which
|
can be viewed as a
<term>
formal computation
|
#1999
Here we emphasize the connection to Montague semanticswhich can be viewed as a formal computation of the logical form. |
|
WH-questions
</term>
. These
<term>
models
</term>
,
|
which
|
are built from
<term>
shallow linguistic
|
#2146
These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent a user's informational goals. |
|
are employed to predict target variables
|
which
|
represent a
<term>
user 's informational
|
#2162
These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent a user's informational goals. |
|
multi-source approach to question answering
</term>
|
which
|
is based on combining the results from
|
#2334
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 answeringwhich is based on combining the results from different answering agents searching for answers in multiple corpora. |
|
word-based models
</term>
. Our empirical results ,
|
which
|
hold for all examined
<term>
language pairs
|
#2592
Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translations. |
|
<term>
predicate argument structures
</term>
,
|
which
|
is central to our
<term>
IE paradigm
</term>
|
#3742
We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm. |
|
data
</term>
. We describe a new approach
|
which
|
involves clustering
<term>
subcategorization
|
#3907
We describe a new approach which involves clustering subcategorization frame (SCF) distributions using the Information Bottleneck and nearest neighbour methods. |
|
<term>
evaluation scheme
</term>
is proposed
|
which
|
accounts for the effect of
<term>
polysemy
|
#3945
A novel evaluation scheme is proposed which accounts for the effect of polysemy on the clusters, offering us a good insight into the potential and limitations of semantically classifying undisambiguated SCF data. |
|
English-Chinese parallel corpora
</term>
,
|
which
|
are then used for disambiguating the
<term>
|
#4840
In 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. |
|
that the
<term>
features
</term>
in terms of
|
which
|
we formulate our
<term>
heuristic principles
|
#5249
The results show that the features in terms of which we formulate our heuristic principles have significant predictive power, and that rules that closely resemble our Horn clauses can be learnt automatically from these features. |