#21960A method of sense resolution is proposed that is based on WordNet, an on-line lexical database that incorporates semantic relations (synonymy, antonymy, hyponymy, meronymy, causal and troponymic entailment) as labeled pointers between word senses.
other,16-5-H91-1077,ak
polysemous word
</term>
will be used as a
<term>
key
</term>
to search a
<term>
large corpus
</term>
#22116Or, (2) the context of the polysemous word will be used as akey to search a large corpus; all words found to occur in that context will be noted; WordNet will then be used to estimate the semantic distance from those words to the alternative senses of the polysemous word; and that sense will be chosen that is closest in meaning to other words occurring in the same context.
other,10-2-H91-1077,ak
</term>
, it is easy to retrieve sets of
<term>
semantically related words
</term>
, a facility that will be used for
#21990With WordNet, it is easy to retrieve sets ofsemantically related words, a facility that will be used for sense resolution during text processing, as follows.
other,5-3-H91-1077,ak
When a
<term>
word
</term>
with multiple
<term>
senses
</term>
is encountered , one of two procedures
#22015When a word with multiplesenses is encountered, one of two procedures will be followed.
other,54-4-H91-1077,ak
for these derived strings ; and that
<term>
sense
</term>
will be chosen that corresponds to
#22081Either, (1) words related in meaning to the alternative senses of the polysemous word will be retrieved; new strings will be derived by substituting these related words into the context of the polysemous word; a large textual corpus will then be searched for these derived strings; and thatsense will be chosen that corresponds to the derived string that is found most often in the corpus.
other,50-5-H91-1077,ak
from those
<term>
words
</term>
to the
<term>
alternative senses
</term>
of the
<term>
polysemous word
</term>
#22150Or, (2) the context of the polysemous word will be used as a key to search a large corpus; all words found to occur in that context will be noted; WordNet will then be used to estimate the semantic distance from those words to thealternative senses of the polysemous word; and that sense will be chosen that is closest in meaning to other words occurring in the same context.
other,54-5-H91-1077,ak
<term>
alternative senses
</term>
of the
<term>
polysemous word
</term>
; and that
<term>
sense
</term>
will
#22154Or, (2) the context of the polysemous word will be used as a key to search a large corpus; all words found to occur in that context will be noted; WordNet will then be used to estimate the semantic distance from those words to the alternative senses of thepolysemous word; and that sense will be chosen that is closest in meaning to other words occurring in the same context.
other,6-5-H91-1077,ak
<term>
corpus
</term>
. Or , ( 2 ) the
<term>
context
</term>
of the
<term>
polysemous word
</term>
#22106Or, (2) thecontext of the polysemous word will be used as a key to search a large corpus; all words found to occur in that context will be noted; WordNet will then be used to estimate the semantic distance from those words to the alternative senses of the polysemous word; and that sense will be chosen that is closest in meaning to other words occurring in the same context.
other,30-5-H91-1077,ak
words
</term>
found to occur in that
<term>
context
</term>
will be noted ;
<term>
WordNet
</term>
#22130Or, (2) the context of the polysemous word will be used as a key to search a large corpus; all words found to occur in thatcontext will be noted; WordNet will then be used to estimate the semantic distance from those words to the alternative senses of the polysemous word; and that sense will be chosen that is closest in meaning to other words occurring in the same context.
other,43-5-H91-1077,ak
</term>
will then be used to estimate the
<term>
semantic distance
</term>
from those
<term>
words
</term>
to the
#22143Or, (2) the context of the polysemous word will be used as a key to search a large corpus; all words found to occur in that context will be noted; WordNet will then be used to estimate thesemantic distance from those words to the alternative senses of the polysemous word; and that sense will be chosen that is closest in meaning to other words occurring in the same context.
other,70-5-H91-1077,ak
closest in
<term>
meaning
</term>
to other
<term>
words
</term>
occurring in the same
<term>
context
#22170Or, (2) the context of the polysemous word will be used as a key to search a large corpus; all words found to occur in that context will be noted; WordNet will then be used to estimate the semantic distance from those words to the alternative senses of the polysemous word; and that sense will be chosen that is closest in meaning to otherwords occurring in the same context.
other,15-4-H91-1077,ak
<term>
alternative senses
</term>
of the
<term>
polysemous word
</term>
will be retrieved ; new strings will
#22042Either, (1) words related in meaning to the alternative senses of thepolysemous word will be retrieved; new strings will be derived by substituting these related words into the context of the polysemous word; a large textual corpus will then be searched for these derived strings; and that sense will be chosen that corresponds to the derived string that is found most often in the corpus.
lr,15-1-H91-1077,ak
on
<term>
WordNet
</term>
, an on-line
<term>
lexical database
</term>
that incorporates
<term>
semantic relations
#21953A method of sense resolution is proposed that is based on WordNet, an on-linelexical database that incorporates semantic relations (synonymy, antonymy, hyponymy, meronymy, causal and troponymic entailment) as labeled pointers between word senses.
tech,3-1-H91-1077,ak
specific
<term>
corpora
</term>
. A method of
<term>
sense resolution
</term>
is proposed that is based on
<term>
#21941A method ofsense resolution is proposed that is based on WordNet, an on-line lexical database that incorporates semantic relations (synonymy, antonymy, hyponymy, meronymy, causal and troponymic entailment) as labeled pointers between word senses.
tech,12-6-H91-1077,ak
practical applications to problems of
<term>
information retrieval
</term>
,
<term>
mechanical translation
</term>
#22189If successful, this procedure could have practical applications to problems ofinformation retrieval, mechanical translation, intelligent tutoring systems, and elsewhere.
lr,71-4-H91-1077,ak
string that is found most often in the
<term>
corpus
</term>
. Or , ( 2 ) the
<term>
context
</term>
#22098Either, (1) words related in meaning to the alternative senses of the polysemous word will be retrieved; new strings will be derived by substituting these related words into the context of the polysemous word; a large textual corpus will then be searched for these derived strings; and that sense will be chosen that corresponds to the derived string that is found most often in thecorpus.
other,11-4-H91-1077,ak
related in
<term>
meaning
</term>
to the
<term>
alternative senses
</term>
of the
<term>
polysemous word
</term>
#22038Either, (1) words related in meaning to thealternative senses of the polysemous word will be retrieved; new strings will be derived by substituting these related words into the context of the polysemous word; a large textual corpus will then be searched for these derived strings; and that sense will be chosen that corresponds to the derived string that is found most often in the corpus.
tool,35-5-H91-1077,ak
<term>
context
</term>
will be noted ;
<term>
WordNet
</term>
will then be used to estimate the
#22135Or, (2) the context of the polysemous word will be used as a key to search a large corpus; all words found to occur in that context will be noted;WordNet will then be used to estimate the semantic distance from those words to the alternative senses of the polysemous word; and that sense will be chosen that is closest in meaning to other words occurring in the same context.
other,75-5-H91-1077,ak
<term>
words
</term>
occurring in the same
<term>
context
</term>
. If successful , this procedure
#22175Or, (2) the context of the polysemous word will be used as a key to search a large corpus; all words found to occur in that context will be noted; WordNet will then be used to estimate the semantic distance from those words to the alternative senses of the polysemous word; and that sense will be chosen that is closest in meaning to other words occurring in the samecontext.
#21962A method of sense resolution is proposed that is based on WordNet, an on-line lexical database that incorporates semantic relations (synonymy,antonymy, hyponymy, meronymy, causal and troponymic entailment) as labeled pointers between word senses.