#1316Sentence 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.
other,15-1-P03-1002,ak
takes advantage of
<term>
predicate-argument
structures
</term>
. We also introduce a new way of
#3728In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures.
#3741We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm.
other,8-4-P03-1002,ak
claim that accurate
<term>
predicate-argument
structures
</term>
enable high quality
<term>
IE results
#3783The experimental results prove our claim that accurate predicate-argument structures enable high quality IE results.
new method for the representation of NLP
structures
within
<term>
reranking approaches
</term>
#5440We describe a new method for the representation of NLP structures within reranking approaches.
techniques described generalize naturally to NLP
structures
other than
<term>
parse trees
</term>
. This
#5575Although our experiments are focused on parsing, the techniques described generalize naturally to NLP structures other than parse trees.
other,12-4-I05-4007,ak
rules
</term>
to predict
<term>
Chinese wordnet
structure
</term>
based on
<term>
English wordnet
</term>
#7142In particular, we propose a set of inference rules to predict Chinese wordnet structure based on English wordnet and English-Chinese translation relations.
other,7-1-P05-1032,ak
this paper we describe a novel
<term>
data
structure
</term>
for
<term>
phrase-based statistical
#8767In this paper we describe a novel data structure for phrase-based statistical machine translation which allows for the retrieval of arbitrarily long phrases while simultaneously using less memory than is required by current decoder implementations.
other,16-2-P05-1032,ak
</term>
in our
<term>
suffix array-based data
structure
</term>
. We show how sampling can be used
#8814We detail the computational complexity and average retrieval times for looking up phrase translations in our suffix array-based data structure.
</term>
. We demonstrate that for certain field
structured
extraction tasks , such as classified advertisements
#9041We demonstrate that for certain field structured extraction tasks, such as classified advertisements and bibliographic citations, small amounts of prior knowledge can be used to learn effective models in a primarily unsupervised fashion.
HMM learning
</term>
fails to learn useful
structure
in either of our
<term>
domains
</term>
. However
#9096Although hidden Markov models (HMMs) provide a suitable generative model for field structured text, general unsupervised HMM learning fails to learn useful structure in either of our domains.
dramatically improve the quality of the learned
structure
by exploiting simple prior knowledge of
#9114However, one can dramatically improve the quality of the learned structure by exploiting simple prior knowledge of the desired solutions.
<term>
core argument frame
</term>
is a joint
structure
, with strong
<term>
dependencies
</term>
between
#10080This stands in stark contrast to the linguistic observation that a core argument frame is a joint structure, with strong dependencies between arguments.
other,13-1-P05-2016,ak
tree-to-tree translation
</term>
of
<term>
dependency
structures
</term>
. The only
<term>
bilingual resource
#10580We present a Czech-English statistical machine translation system which performs tree-to-tree translation of dependency structures.
, it is argued , can be resolved if some
structure
is imposed on the available
<term>
knowledge
#11628Both problems, it is argued, can be resolved if some structure is imposed on the available knowledge prior to content determination.
formalism
</term>
for the combination of various
structures
:
<term>
strings
</term>
,
<term>
trees
</term>
#11994This paper proposes a generic mathematical formalism for the combination of various structures: strings, trees, dags, graphs, and products of them.
polarization
</term>
of the objects of the elementary
structures
controls the
<term>
saturation
</term>
of the
#12017The polarization of the objects of the elementary structures controls the saturation of the final structure.
controls the
<term>
saturation
</term>
of the final
structure
. This
<term>
formalism
</term>
is both elementary
#12024The polarization of the objects of the elementary structures controls the saturation of the final structure.
our method is to utilize certain layout
structures
and
<term>
linguistic pattern
</term>
. By
#12373The idea behind our method is to utilize certain layout structures and linguistic pattern.
other,9-1-P06-4011,ak
computational analysis
</term>
of
<term>
move
structures
</term>
in
<term>
abstracts
</term>
of research
#12643This paper introduces a method for computational analysis of move structures in abstracts of research articles.