#142Several 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.
effectiveness of these
<term>
indices
</term>
can
be obtained . To support engaging human
#202Despite the small size of the databases used some results about the effectiveness of these indicescan be obtained.
</term>
and
<term>
scenario templates
</term>
-
can
be used to enhance access to
<term>
text
#298In 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.
</term>
showed that
<term>
assessors
</term>
can
differentiate
<term>
native from non-native
#635A language learning experiment showed that assessorscan differentiate native from non-native language essays in less than 100 words.
<term>
LCS-Marine
</term>
, tactical personnel
can
converse with their logistics system to
#833Using LCS-Marine, tactical personnel can converse with their logistics system to place a supply or information request.
#865Requestorscan also instruct the system to notify them when the status of a request changes or when a request is complete.
show how research in
<term>
generation
</term>
can
be adapted to
<term>
dialog systems
</term>
#1001We show how research in generationcan 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.
knowledge-based generation systems
</term>
can
be overcome by employing
<term>
machine learning
#1018We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systemscan be overcome by employing machine learning techniques.
range concatenation languages [ RCL ]
</term>
can
be parsed in
<term>
polynomial time
</term>
#1630In particular, range concatenation languages [RCL]can be parsed in polynomial time and many classical grammatical formalisms can be translated into equivalent RCGs without increasing their worst-case parsing time complexity.
<term>
classical grammatical formalisms
</term>
can
be translated into equivalent
<term>
RCGs
#1641In particular, range concatenation languages [RCL] can be parsed in polynomial time and many classical grammatical formalismscan be translated into equivalent RCGs without increasing their worst-case parsing time complexity.
, any
<term>
tree adjoining grammar
</term>
can
be parsed in O ( n6 )
<term>
time
</term>
.
#1669For example, after translation into an equivalent RCG, any tree adjoining grammarcan be parsed in O(n6) time.
performance
</term>
of a
<term>
search engine
</term>
can
be improved dramatically by incorporating
#1881I show that the performance of a search enginecan be improved dramatically by incorporating an approximation of the formal analysis that is compatible with the search engine's operational semantics.
connection to
<term>
Montague semantics
</term>
which
can
be viewed as a formal computation of the
#2001Here we emphasize the connection to Montague semantics which can be viewed as a formal computation of the logical form.
</term>
produced with trainable components
can
compete with
<term>
hand-crafted template-based
#2042Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced with trainable components can compete with hand-crafted template-based or rule-based approaches.
</term>
that is surprisingly close to what
can
be achieved using conventional
<term>
word-trigram
#2245The method combines domain independent acoustic models with off-the-shelf classifiers to give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription.
showed that
<term>
human annotators
</term>
can
reliably differentiate between semantically
#2490We conducted an annotation experiment and showed that human annotatorscan reliably differentiate between semantically coherent and incoherent speech recognition hypotheses.
suggest that the highest levels of performance
can
be obtained through relatively simple means
#2608Our 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.
, we show how
<term>
training data
</term>
can
be supplemented with
<term>
text
</term>
from
#3038In this paper, we show how training datacan be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams.
algorithms
</term>
. The results show that it
can
provide a significant improvement in
<term>
#3277The results show that it can provide a significant improvement in alignment quality.
all the three strategies together and thus
can
suppress all the shortcomings of different
#3555Cooperative Model incorporates all the three strategies together and thus can suppress all the shortcomings of different strategies and has all the advantages of the three strategies.