#14336Our solution to these problems is to make use of expectations, based both on knowledge of surface English and onworld knowledge of the situation being described.
other,19-4-P82-1035,ak
context
</term>
, constrain the possible
<term>
word-senses
</term>
of
<term>
words
</term>
with multiple
#14363These syntactic and semantic expectations can be used to figure out unknown words from context, constrain the possibleword-senses of words with multiple meanings (ambiguity), fill in missing words (ellipsis), and resolve referents (anaphora).
other,12-1-P82-1035,ak
designed under the assumption that the
<term>
input text
</term>
will be in reasonably neat form ,
#14245Most large text-understanding systems have been designed under the assumption that theinput text will be in reasonably neat form, e.g., newspaper stories and other edited texts.
other,21-4-P82-1035,ak
possible
<term>
word-senses
</term>
of
<term>
words
</term>
with multiple
<term>
meanings
</term>
#14365These syntactic and semantic expectations can be used to figure out unknown words from context, constrain the possible word-senses ofwords with multiple meanings (ambiguity), fill in missing words (ellipsis), and resolve referents (anaphora).