#25599Syntactic analysis of the English coordinate sentences is one of the most difficult problems formachine translation ( MT ) systems.
tech,6-6-A94-1007,ak
The
<term>
model
</term>
is based on a
<term>
balance matching operation
</term>
for two lists of the
<term>
feature
#25706The model is based on abalance matching operation for two lists of the feature sets, which provides four effects: the reduction of analysis cost, the improvement of word disambiguation, the interpretation of ellipses, and robust analysis.
model,12-3-A94-1007,ak
<term>
candidates
</term>
, the correct
<term>
syntactic structure
</term>
formed by an individual
<term>
coordinate
#25618The problem is selecting, from all possible candidates, the correctsyntactic structure formed by an individual coordinate conjunction, i.e. determining which constituents are coordinated by the conjunction.
tech,9-4-A94-1007,ak
structures
</term>
are produced that
<term>
MT systems
</term>
can not select the correct one ,
#25646Typically, so many possible structures are produced thatMT systems cannot select the correct one, even if the grammars allow to write the rules in the simple notations.
model,26-4-A94-1007,ak
<term>
grammars
</term>
allow to write the
<term>
rules
</term>
in the simple notations . This paper
#25663Typically, so many possible structures are produced that MT systems cannot select the correct one, even if the grammars allow to write therules in the simple notations.
model,1-6-A94-1007,ak
of the
<term>
parallelism
</term>
. The
<term>
model
</term>
is based on a
<term>
balance matching
#25701Themodel is based on a balance matching operation for two lists of the feature sets, which provides four effects: the reduction of analysis cost, the improvement of word disambiguation, the interpretation of ellipses, and robust analysis.
tech,40-6-A94-1007,ak
</term>
of
<term>
ellipses
</term>
, and
<term>
robust analysis
</term>
. This
<term>
model
</term>
was practically
#25740The model is based on a balance matching operation for two lists of the feature sets, which provides four effects: the reduction of analysis cost, the improvement of word disambiguation, the interpretation of ellipses, androbust analysis.
other,8-3-A94-1007,ak
problem is selecting , from all possible
<term>
candidates
</term>
, the correct
<term>
syntactic structure
#25614The problem is selecting, from all possiblecandidates, the correct syntactic structure formed by an individual coordinate conjunction, i.e. determining which constituents are coordinated by the conjunction.
other,29-3-A94-1007,ak
constituents
</term>
are coordinated by the
<term>
conjunction
</term>
. Typically , so many possible
<term>
#25635The problem is selecting, from all possible candidates, the correct syntactic structure formed by an individual coordinate conjunction, i.e. determining which constituents are coordinated by theconjunction.
other,10-1-A94-1007,ak
<term>
English sentences
</term>
including
<term>
coordinate conjunctions
</term>
such as and , or , but and the equivalent
#25570The authors propose a model for analyzing English sentences includingcoordinate conjunctions such as and, or, but and the equivalent words.
measure(ment),18-7-A94-1007,ak
system
</term>
, and provided about 75 %
<term>
accuracy
</term>
in the practical translation use
#25761This model was practically implemented and incorporated into the English-Japanese MT system, and provided about 75%accuracy in the practical translation use.