|
power of
<term>
phrasal SMT
</term>
with the
|
linguistic
|
generality available in a
<term>
parser
</term>
|
#9304
We describe an efficient decoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser. |
other,8-3-P86-1011,bq |
turn to a discussion comparing the
<term>
|
linguistic
|
expressiveness
</term>
of the two
<term>
formalisms
|
#14616
We then turn to a discussion comparing thelinguistic expressiveness of the two formalisms. |
other,11-1-P86-1038,bq |
of
<term>
features
</term>
to describe
<term>
|
linguistic
|
objects
</term>
. Although
<term>
computational
|
#14634
Unification-based grammar formalisms use structures containing sets of features to describelinguistic objects. |
other,4-4-C88-2162,bq |
learning
</term>
. We introduced a new
<term>
|
linguistic
|
representation
</term>
, the
<term>
Dynamic
|
#15790
We introduced a newlinguistic representation, the Dynamic Hierarchical Phrasal Lexicon (DHPL) [Zernik88], to facilitate language acquisition. |
tech,18-2-H92-1060,bq |
</term>
already in place for the full
<term>
|
linguistic
|
analysis component
</term>
. Robust
<term>
|
#19382
This robust parsing capability was achieved through minor extensions of pre-existing components already in place for the fulllinguistic analysis component. |
other,3-7-C88-2162,bq |
identified two tasks : First , how
<term>
|
linguistic
|
concepts
</term>
are acquired from
<term>
training
|
#15844
First, howlinguistic concepts are acquired from training examples and organized in a hierarchy; this task was discussed in previous papers [Zernik87]. |
other,16-8-C88-2162,bq |
hierarchy
</term>
is used in predicting new
<term>
|
linguistic
|
concepts
</term>
. Thus , a
<term>
program
</term>
|
#15884
Second, we show in this paper how a lexical hierarchy is used in predicting newlinguistic concepts. |
tech,4-2-N03-1026,bq |
Our
<term>
system
</term>
incorporates a
<term>
|
linguistic
|
parser/generator
</term>
for
<term>
LFG
</term>
|
#2812
Our system incorporates alinguistic parser/generator for LFG, a transfer component for parse reduction operating on packed parse forests, and a maximum-entropy model for stochastic output selection. |
other,6-2-C86-1132,bq |
RAREAS
</term>
draws on several kinds of
<term>
|
linguistic
|
and non-linguistic knowledge
</term>
and
|
#13952
RAREAS draws on several kinds oflinguistic and non-linguistic knowledge and mirrors a forecaster's apparent tendency to ascribe less precise temporal adverbs to more remote meteorological events. |
other,13-4-J86-3001,bq |
purposes
</term>
, expressed in each of the
<term>
|
linguistic
|
segments
</term>
as well as relationships
|
#14185
The intentional structure captures the discourse-relevant purposes, expressed in each of thelinguistic segments as well as relationships among them. |
other,12-3-N04-1022,bq |
that incorporate different levels of
<term>
|
linguistic
|
information
</term>
from
<term>
word strings
|
#6587
We describe a hierarchy of loss functions that incorporate different levels oflinguistic information from word strings, word-to-word alignments from an MT system, and syntactic structure from parse-trees of source and target language sentences. |
other,15-4-H92-1026,bq |
grammar
</term>
tailoring via the usual
<term>
|
linguistic
|
introspection
</term>
in the hope of generating
|
#18996
This stands in contrast to the usual approach of further grammar tailoring via the usuallinguistic introspection in the hope of generating the correct parse. |
other,27-2-J90-3002,bq |
dictionary
</term>
on the basis of a
<term>
|
linguistic
|
theory
</term>
. If we want valuable
<term>
|
#17257
The basic goal in building that editor was to provide an adequate tool to help lexicologists produce a valid and coherent dictionary on the basis of alinguistic theory. |
other,27-1-C04-1112,bq |
classification ( maximum entropy )
</term>
with
<term>
|
linguistic
|
information
</term>
. Instead of building
|
#6006
In this paper, we present a corpus-based supervised word sense disambiguation (WSD) system for Dutch which combines statistical classification (maximum entropy) withlinguistic information. |
other,7-2-P01-1070,bq |
</term>
, which are built from
<term>
shallow
|
linguistic
|
features
</term>
of
<term>
questions
</term>
|
#2151
These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent a user's informational goals. |
tech,27-1-H92-1060,bq |
a
<term>
question
</term>
when a full
<term>
|
linguistic
|
analysis
</term>
fails . This
<term>
robust
|
#19360
This paper describes an extension to the MIT ATIS (Air Travel Information Service) system, which allows it to answer a question when a fulllinguistic analysis fails. |
other,5-3-A94-1011,bq |
</term>
. A novel method for adding
<term>
|
linguistic
|
annotation
</term>
to
<term>
corpora
</term>
|
#19950
A novel method for addinglinguistic annotation to corpora is presented which involves using a statistical POS tagger in conjunction with unsupervised structure finding methods to derive notions of noun group, verb group, and so on which is inherently extensible to more sophisticated annotation, and does not require a pre-tagged corpus to fit. |
tech,12-4-C90-3063,bq |
statistics
</term>
on the output of other
<term>
|
linguistic
|
tools
</term>
. An experiment was performed
|
#16667
The scheme was implemented by gathering statistics on the output of otherlinguistic tools. |
other,17-2-C88-2162,bq |
does not readily lend itself in the
<term>
|
linguistic
|
domain
</term>
. For another ,
<term>
linguistic
|
#15767
For one thing, learning methodology applicable in general domains does not readily lend itself in thelinguistic domain. |
other,1-3-J86-3001,bq |
<term>
attentional state
</term>
) . The
<term>
|
linguistic
|
structure
</term>
consists of segments of
|
#14157
Thelinguistic structure consists of segments of the discourse into which the utterances naturally aggregate. |