other,11-2-P82-1035,bq |
natural language texts
</term>
e.g. ,
<term>
|
memos
|
</term>
, rough
<term>
drafts
</term>
,
<term>
|
#12985
However, a great deal of natural language texts e.g.,memos, rough drafts, conversation transcripts etc., have features that differ significantly from neat texts, posing special problems for readers, such as misspelled words, missing words, poor syntactic construction, missing periods, etc. |
other,21-3-P82-1035,bq |
<term>
surface English
</term>
and on
<term>
|
world knowledge
|
</term>
of the situation being described
|
#13047
Our 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,39-4-P82-1035,bq |
<term>
elllpsis
</term>
) , and resolve
<term>
|
referents
|
</term>
(
<term>
anaphora
</term>
) . This method
|
#13094
These syntactic and semantic expectations can be used to figure out unknown words from context, constrain the possible word-senses of words with multiple meanings (ambiguity), fill in missing words (elllpsis), and resolvereferents (anaphora). |
other,1-4-P82-1035,bq |
situation being described . These
<term>
|
syntactic and semantic expectations
|
</term>
can be used to figure out
<term>
unknown
|
#13056
Thesesyntactic and semantic expectations can be used to figure out unknown words from context, constrain the possible word-senses of words with multiple meanings (ambiguity), fill in missing words (elllpsis), and resolve referents (anaphora). |
other,16-2-P82-1035,bq |
</term>
, rough
<term>
drafts
</term>
,
<term>
|
conversation transcripts
|
</term>
etc. , have features that differ
|
#12990
However, a great deal of natural language texts e.g., memos, rough drafts,conversation transcripts etc., have features that differ significantly from neat texts, posing special problems for readers, such as misspelled words, missing words, poor syntactic construction, missing periods, etc. |
other,37-2-P82-1035,bq |
special problems for readers , such as
<term>
|
misspelled words
|
</term>
,
<term>
missing words
</term>
,
<term>
|
#13011
However, a great deal of natural language texts e.g., memos, rough drafts, conversation transcripts etc., have features that differ significantly from neat texts, posing special problems for readers, such asmisspelled words, missing words, poor syntactic construction, missing periods, etc. |
other,13-1-P82-1035,bq |
under the assumption that the input
<term>
|
text
|
</term>
will be in reasonably neat form ,
|
#12957
Most large text-understanding systems have been designed under the assumption that the inputtext will be in reasonably neat form, e.g., newspaper stories and other edited texts. |
tech,2-1-P82-1035,bq |
executed to yield the answer . Most large
<term>
|
text-understanding systems
|
</term>
have been designed under the assumption
|
#12946
Most largetext-understanding systems have been designed under the assumption that the input text will be in reasonably neat form, e.g., newspaper stories and other edited texts. |
other,17-3-P82-1035,bq |
</term>
, based both on knowledge of
<term>
|
surface English
|
</term>
and on
<term>
world knowledge
</term>
|
#13043
Our solution to these problems is to make use of expectations, based both on knowledge ofsurface English and on world knowledge of the situation being described. |
other,40-2-P82-1035,bq |
such as
<term>
misspelled words
</term>
,
<term>
|
missing words
|
</term>
,
<term>
poor syntactic construction
|
#13014
However, a great deal of natural language texts e.g., memos, rough drafts, conversation transcripts etc., have features that differ significantly from neat texts, posing special problems for readers, such as misspelled words,missing words, poor syntactic construction, missing periods, etc. |
other,14-4-P82-1035,bq |
out
<term>
unknown words
</term>
from
<term>
|
context
|
</term>
, constrain the possible
<term>
word-senses
|
#13069
These syntactic and semantic expectations can be used to figure out unknown words fromcontext, constrain the possible word-senses of words with multiple meanings (ambiguity), fill in missing words (elllpsis), and resolve referents (anaphora). |
other,43-2-P82-1035,bq |
</term>
,
<term>
missing words
</term>
,
<term>
|
poor syntactic construction
|
</term>
,
<term>
missing periods
</term>
, etc
|
#13017
However, a great deal of natural language texts e.g., memos, rough drafts, conversation transcripts etc., have features that differ significantly from neat texts, posing special problems for readers, such as misspelled words, missing words,poor syntactic construction, missing periods, etc. |
other,19-4-P82-1035,bq |
context
</term>
, constrain the possible
<term>
|
word-senses
|
</term>
of
<term>
words with multiple meanings
|
#13074
These 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 (elllpsis), and resolve referents (anaphora). |
other,26-2-P82-1035,bq |
features that differ significantly from
<term>
|
neat texts
|
</term>
, posing special problems for readers
|
#13000
However, a great deal of natural language texts e.g., memos, rough drafts, conversation transcripts etc., have features that differ significantly fromneat texts, posing special problems for readers, such as misspelled words, missing words, poor syntactic construction, missing periods, etc. |
tool,21-5-P82-1035,bq |
<term>
computer program
</term>
called
<term>
|
NOMAD
|
</term>
, which understands
<term>
scruffy
|
#13120
This method of using expectations to aid the understanding of scruffy texts has been incorporated into a working computer program calledNOMAD, which understands scruffy texts in the domain of Navy messages. |
other,14-2-P82-1035,bq |
</term>
e.g. ,
<term>
memos
</term>
, rough
<term>
|
drafts
|
</term>
,
<term>
conversation transcripts
</term>
|
#12988
However, a great deal of natural language texts e.g., memos, roughdrafts, conversation transcripts etc., have features that differ significantly from neat texts, posing special problems for readers, such as misspelled words, missing words, poor syntactic construction, missing periods, etc. |
other,41-4-P82-1035,bq |
and resolve
<term>
referents
</term>
(
<term>
|
anaphora
|
</term>
) . This method of using
<term>
expectations
|
#13096
These syntactic and semantic expectations can be used to figure out unknown words from context, constrain the possible word-senses of words with multiple meanings (ambiguity), fill in missing words (elllpsis), and resolve referents (anaphora). |
other,26-4-P82-1035,bq |
words with multiple meanings
</term>
(
<term>
|
ambiguity
|
</term>
) , fill in
<term>
missing words
</term>
|
#13081
These syntactic and semantic expectations can be used to figure out unknown words from context, constrain the possible word-senses of words with multiple meanings (ambiguity), fill in missing words (elllpsis), and resolve referents (anaphora). |
other,27-1-P82-1035,bq |
<term>
newspaper stories
</term>
and other
<term>
|
edited texts
|
</term>
. However , a great deal of
<term>
|
#12971
Most large text-understanding systems have been designed under the assumption that the input text will be in reasonably neat form, e.g., newspaper stories and otheredited texts. |
other,31-4-P82-1035,bq |
(
<term>
ambiguity
</term>
) , fill in
<term>
|
missing words
|
</term>
(
<term>
elllpsis
</term>
) , and resolve
|
#13086
These syntactic and semantic expectations can be used to figure out unknown words from context, constrain the possible word-senses of words with multiple meanings (ambiguity), fill inmissing words (elllpsis), and resolve referents (anaphora). |