#21968A 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.
tech,15-6-H91-1077,ak
<term>
information retrieval
</term>
,
<term>
mechanical translation
</term>
,
<term>
intelligent tutoring systems
#22192If successful, this procedure could have practical applications to problems of information retrieval,mechanical translation, intelligent tutoring systems, and elsewhere.
tech,18-6-H91-1077,ak
<term>
mechanical translation
</term>
,
<term>
intelligent tutoring systems
</term>
, and elsewhere . A system is described
#22195If successful, this procedure could have practical applications to problems of information retrieval, mechanical translation,intelligent tutoring systems, and elsewhere.
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,5-4-H91-1077,ak
will be followed . Either , ( 1 )
<term>
words
</term>
related in
<term>
meaning
</term>
to
#22032Either, (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 the corpus.
lr,40-4-H91-1077,ak
the
<term>
polysemous word
</term>
; a
<term>
large textual corpus
</term>
will then be searched for these derived
#22067Either, (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; alarge 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.
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.
lr,20-5-H91-1077,ak
used as a
<term>
key
</term>
to search a
<term>
large corpus
</term>
; all
<term>
words
</term>
found to occur
#22120Or, (2) the context of the polysemous word will be used as a key to search alarge 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,24-5-H91-1077,ak
search a
<term>
large corpus
</term>
; all
<term>
words
</term>
found to occur in that
<term>
context
#22124Or, (2) the context of the polysemous word will be used as a key to search a large corpus; allwords 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,39-1-H91-1077,ak
</term>
) as labeled pointers between
<term>
word senses
</term>
. With
<term>
WordNet
</term>
, it is
#21977A 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 betweenword senses.
tech,24-2-H91-1077,ak
<term>
sense resolution
</term>
during
<term>
text processing
</term>
, as follows . When a
<term>
word
</term>
#22004With WordNet, it is easy to retrieve sets of semantically related words, a facility that will be used for sense resolution duringtext processing, as follows.
tech,21-2-H91-1077,ak
, a facility that will be used for
<term>
sense resolution
</term>
during
<term>
text processing
</term>
#22001With WordNet, it is easy to retrieve sets of semantically related words, a facility that will be used forsense resolution during text processing, as follows.
other,67-5-H91-1077,ak
</term>
will be chosen that is closest in
<term>
meaning
</term>
to other
<term>
words
</term>
occurring
#22167Or, (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 inmeaning to other words occurring in the same context.
other,8-4-H91-1077,ak
( 1 )
<term>
words
</term>
related in
<term>
meaning
</term>
to the
<term>
alternative senses
</term>
#22035Either, (1) words related inmeaning 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 the corpus.
#21957A method of sense resolution is proposed that is based on WordNet, an on-line lexical database that incorporatessemantic relations (synonymy, antonymy, hyponymy, meronymy, causal and troponymic entailment) as labeled pointers between word senses.
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.
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.
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.
tool,11-1-H91-1077,ak
</term>
is proposed that is based on
<term>
WordNet
</term>
, an on-line
<term>
lexical database
#21949A method of sense resolution is proposed that is based onWordNet, an on-line lexical database that incorporates semantic relations (synonymy, antonymy, hyponymy, meronymy, causal and troponymic entailment) as labeled pointers between word senses.