#67Traditional information retrieval techniques use a histogram of keywords as the document representation but oral communication may offer additional indices such as the time and place of the rejoinder and the attendance.
tech,19-2-H01-1041,ak
mediated by a
<term>
language neutral meaning
representation
</term>
called a
<term>
semantic frame
</term>
#433The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame.
model,26-1-N03-1033,ak
contexts
</term>
via a
<term>
dependency network
representation
</term>
, ( ii ) broad use of
<term>
lexical
#2938We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features.
</term>
. We describe a new method for the
representation
of NLP structures within
<term>
reranking
#5437We describe a new method for the representation of NLP structures within reranking approaches.
other,4-2-P05-1018,ak
</term>
. We present a novel
<term>
entity-based
representation
of discourse
</term>
which is inspired by
#8609We present a novel entity-based representation of discourse which is inspired by Centering Theory and can be computed automatically from raw text.
other,14-3-P05-1018,ak
and show that the proposed
<term>
discourse
representation
</term>
supports the effective learning of
#8642We view coherence assessment as a ranking learning problem and show that the proposed discourse representation supports the effective learning of a ranking function.
model,13-1-P06-1052,ak
</term>
: Given an
<term>
underspecified semantic
representation
( USR )
</term>
of a
<term>
scope ambiguity
#12070We present an efficient algorithm for the redundancy elimination problem: Given an underspecified semantic representation (USR) of a scope ambiguity, compute an USR with fewer mutually equivalent readings.
model,4-2-P06-1052,ak
</term>
operates on
<term>
underspecified chart
representations
</term>
which are derived from
<term>
dominance
#12094The algorithm operates on underspecified chart representations which are derived from dominance graphs; it can be applied to the USRs computed by large-scale grammars.
<term>
path-based inference rules
</term>
to the
representation
of the
<term>
extensional equivalence
</term>
#13129Applications of path-based inference rules to the representation of the extensional equivalence of intensional concepts, and to the explication of inheritance in hierarchies are sketched.
other,27-5-P81-1033,ak
construction
</term>
, and specialized
<term>
ambiguity
representations
</term>
for each type of
<term>
ambiguity
</term>
#14016Focused interaction of this kind is facilitated by a construction-specific approach to flexible parsing, with specialized parsing techniques for each type of construction, and specialized ambiguity representations for each type of ambiguity that a particular construction can give rise to.
other,10-2-P84-1047,ak
the
<term>
structure
</term>
and
<term>
surface
representation
</term>
of
<term>
domain entities
</term>
are
#15058In this approach, the definitions of the structure and surface representation of domain entities are grouped together.
other,26-3-P85-1024,ak
goals
</term>
, rather than upon precise
<term>
representations
</term>
of the preceding
<term>
utterance
</term>
#16002We claim that the advantage of this approach is its reliance upon pragmatic information, including discourse content and conversational goals, rather than upon preciserepresentations of the preceding utterance alone.
other,21-4-C88-1007,ak
relation
</term>
, not as levels of
<term>
textual
representation
</term>
. After introducing this approach
#17966Semantic and other information may still be incorporated, but as constraints on the translation relation, not as levels of textual representation.
model,3-3-C88-2162,ak
linguistic domain . For another ,
<term>
linguistic
representation
</term>
used by
<term>
language processing
#18621For another, linguistic representation used by language processing systems is not geared to learning.
model,4-4-C88-2162,ak
</term>
. We introduced a new
<term>
linguistic
representation
</term>
, the
<term>
Dynamic Hierarchical Phrasal
#18638We introduced a new linguistic representation, the Dynamic Hierarchical Phrasal Lexicon (DHPL) [Zernik88], to facilitate language acquisition.
other,11-4-E91-1012,ak
simple way to construct a very compact
<term>
representation
</term>
of the
<term>
parse forest
</term>
.
#21526Memo-functions also facilitate a simple way to construct a very compactrepresentation of the parse forest.
expressing
<term>
relations
</term>
between
representations
in the form of
<term>
feature structures
</term>
#21668Unification is often the appropriate method for expressing relations between representations in the form of feature structures; however, there are circumstances in which a different approach is desirable.
tech,9-4-P91-1025,ak
<term>
information lattice
</term>
, a
<term>
representation
scheme
</term>
for
<term>
utterances
</term>
#22334The basic ingredients are an information lattice, arepresentation scheme for utterances embedded in contexts, and a mismatch resolution scheme defined in terms of information flow.
other,8-4-A94-1011,ak
a more
<term>
linguistically sophisticated
representation
</term>
of
<term>
documents
</term>
over a
<term>
#25897One of the distinguishing features of a more linguistically sophisticated representation of documents over a word set based representation of them is that linguistically sophisticated units are more frequently individually good predictors of document descriptors (keywords) than single words are.
other,15-4-A94-1011,ak
documents
</term>
over a
<term>
word set based
representation
</term>
of them is that linguistically sophisticated
#25905One of the distinguishing features of a more linguistically sophisticated representation of documents over a word set based representation of them is that linguistically sophisticated units are more frequently individually good predictors of document descriptors (keywords) than single words are.