#25032In order to deal with ambiguity, the MORphological PArser MORPA is provided with aprobabilistic context-free grammar ( PCFG ), i.e. it combines a conventional context-free morphological grammar to filter out ungrammatical segmentations with a probability-based scoring function which determines the likelihood of each successful parse.
other,26-1-E93-1023,ak
generation of multiple analyses for one
<term>
input word
</term>
, many of which are implausible .
#25008One of the major problems one is faced with when decomposing words into their constituent parts is ambiguity: the generation of multiple analyses for oneinput word, many of which are implausible.
other,5-2-E93-1023,ak
implausible . In order to deal with
<term>
ambiguity
</term>
, the
<term>
MORphological PArser MORPA
#25022In order to deal withambiguity, the MORphological PArser MORPA is provided with a probabilistic context-free grammar (PCFG), i.e. it combines a conventional context-free morphological grammar to filter out ungrammatical segmentations with a probability-based scoring function which determines the likelihood of each successful parse.
other,17-1-E93-1023,ak
their
<term>
constituent parts
</term>
is
<term>
ambiguity
</term>
: the generation of multiple analyses
#24999One of the major problems one is faced with when decomposing words into their constituent parts isambiguity: the generation of multiple analyses for one input word, many of which are implausible.
other,47-2-E93-1023,ak
likelihood
</term>
of each successful
<term>
parse
</term>
. Consequently , remaining analyses
#25064In order to deal with ambiguity, the MORphological PArser MORPA is provided with a probabilistic context-free grammar (PCFG), i.e. it combines a conventional context-free morphological grammar to filter out ungrammatical segmentations with a probability-based scoring function which determines the likelihood of each successfulparse.
tech,12-4-E93-1023,ak
<term>
PCFG
</term>
yields good results in
<term>
morphological parsing
</term>
.
<term>
MORPA
</term>
is a fully implemented
#25091Test performance data will show that a PCFG yields good results inmorphological parsing.
other,11-3-E93-1023,ak
analyses can be ordered along a scale of
<term>
plausibility
</term>
.
<term>
Test performance data
</term>
#25077Consequently, remaining analyses can be ordered along a scale ofplausibility.
tech,11-5-E93-1023,ak
parser
</term>
developed for use in a
<term>
text-to-speech conversion system
</term>
. We give an analysis of
<term>
ellipsis
#25105MORPA is a fully implemented parser developed for use in atext-to-speech conversion system.
tech,5-5-E93-1023,ak
MORPA
</term>
is a fully implemented
<term>
parser
</term>
developed for use in a
<term>
text-to-speech
#25099MORPA is a fully implementedparser developed for use in a text-to-speech conversion system.
other,11-1-E93-1023,ak
one is faced with when decomposing
<term>
words
</term>
into their
<term>
constituent parts
#24993One of the major problems one is faced with when decomposingwords into their constituent parts is ambiguity: the generation of multiple analyses for one input word, many of which are implausible.
tool,0-5-E93-1023,ak
<term>
morphological parsing
</term>
.
<term>
MORPA
</term>
is a fully implemented
<term>
parser
#25094Test performance data will show that a PCFG yields good results in morphological parsing.MORPA is a fully implemented parser developed for use in a text-to-speech conversion system.
other,14-1-E93-1023,ak
decomposing
<term>
words
</term>
into their
<term>
constituent parts
</term>
is
<term>
ambiguity
</term>
: the generation
#24996One of the major problems one is faced with when decomposing words into theirconstituent parts is ambiguity: the generation of multiple analyses for one input word, many of which are implausible.
tool,8-2-E93-1023,ak
deal with
<term>
ambiguity
</term>
, the
<term>
MORphological PArser MORPA
</term>
is provided with a
<term>
probabilistic
#25025In order to deal with ambiguity, theMORphological PArser MORPA is provided with a probabilistic context-free grammar (PCFG), i.e. it combines a conventional context-free morphological grammar to filter out ungrammatical segmentations with a probability-based scoring function which determines the likelihood of each successful parse.
other,43-2-E93-1023,ak
function
</term>
which determines the
<term>
likelihood
</term>
of each successful
<term>
parse
</term>
#25060In order to deal with ambiguity, the MORphological PArser MORPA is provided with a probabilistic context-free grammar (PCFG), i.e. it combines a conventional context-free morphological grammar to filter out ungrammatical segmentations with a probability-based scoring function which determines thelikelihood of each successful parse.
lr,27-2-E93-1023,ak
</term>
, i.e. it combines a conventional
<term>
context-free morphological grammar
</term>
to filter out
<term>
ungrammatical
#25044In order to deal with ambiguity, the MORphological PArser MORPA is provided with a probabilistic context-free grammar (PCFG), i.e. it combines a conventionalcontext-free morphological grammar to filter out ungrammatical segmentations with a probability-based scoring function which determines the likelihood of each successful parse.
tech,37-2-E93-1023,ak
ungrammatical segmentations
</term>
with a
<term>
probability-based scoring function
</term>
which determines the
<term>
likelihood
#25054In order to deal with ambiguity, the MORphological PArser MORPA is provided with a probabilistic context-free grammar (PCFG), i.e. it combines a conventional context-free morphological grammar to filter out ungrammatical segmentations with aprobability-based scoring function which determines the likelihood of each successful parse.
other,0-4-E93-1023,ak
scale of
<term>
plausibility
</term>
.
<term>
Test performance data
</term>
will show that a
<term>
PCFG
</term>
#25079Consequently, remaining analyses can be ordered along a scale of plausibility.Test performance data will show that a PCFG yields good results in morphological parsing.
other,33-2-E93-1023,ak
morphological grammar
</term>
to filter out
<term>
ungrammatical segmentations
</term>
with a
<term>
probability-based scoring
#25050In order to deal with ambiguity, the MORphological PArser MORPA is provided with a probabilistic context-free grammar (PCFG), i.e. it combines a conventional context-free morphological grammar to filter outungrammatical segmentations with a probability-based scoring function which determines the likelihood of each successful parse.
lr,7-4-E93-1023,ak
performance data
</term>
will show that a
<term>
PCFG
</term>
yields good results in
<term>
morphological
#25086Test performance data will show that aPCFG yields good results in morphological parsing.