other,1-4-P82-1035,bq situation being described . These <term> syntactic and semantic expectations </term> can be used to figure out <term> unknown
other,6-2-P82-1035,bq </term> . However , a great deal of <term> natural language texts </term> e.g. , <term> memos </term> , rough <term>
other,16-2-P82-1035,bq </term> , rough <term> drafts </term> , <term> conversation transcripts </term> etc. , have features that differ
other,11-4-P82-1035,bq expectations </term> can be used to figure out <term> unknown words </term> from <term> context </term> , constrain
other,10-5-P82-1035,bq </term> to aid the understanding of <term> scruffy texts </term> has been incorporated into a working
tech,2-1-P82-1035,bq executed to yield the answer . Most large <term> text-understanding systems </term> have been designed under the assumption
other,25-5-P82-1035,bq <term> NOMAD </term> , which understands <term> scruffy texts </term> in the domain of Navy messages .
other,21-3-P82-1035,bq <term> surface English </term> and on <term> world knowledge </term> of the situation being described
other,19-4-P82-1035,bq context </term> , constrain the possible <term> word-senses </term> of <term> words with multiple meanings
other,4-5-P82-1035,bq anaphora </term> ) . This method of using <term> expectations </term> to aid the understanding of <term>
other,13-1-P82-1035,bq under the assumption that the input <term> text </term> will be in reasonably neat form ,
hide detail