tech,1-1-P80-1019,bq </term> are also discussed . Current <term> natural language interfaces </term> have concentrated largely on determining
other,11-1-P80-1019,bq largely on determining the literal <term> meaning </term> of <term> input </term> from their <term>
other,13-1-P80-1019,bq the literal <term> meaning </term> of <term> input </term> from their <term> users </term> . While
other,16-1-P80-1019,bq </term> of <term> input </term> from their <term> users </term> . While such <term> decoding </term>
tech,2-2-P80-1019,bq their <term> users </term> . While such <term> decoding </term> is an essential underpinning , much
tech,13-2-P80-1019,bq underpinning , much recent work suggests that <term> natural language interfaces </term> will never appear cooperative or
other,27-2-P80-1019,bq unless they also incorporate numerous <term> non-literal aspects of communication </term> , such as robust <term> communication
other,35-2-P80-1019,bq communication </term> , such as robust <term> communication procedures </term> . This paper defends that view ,
other,24-3-P80-1019,bq best way to implement many of these <term> non-literal aspects of communication </term> ; that the new technology of powerful
tech,35-3-P80-1019,bq that the new technology of powerful <term> personal computers </term> with integral <term> graphics displays
tech,39-3-P80-1019,bq personal computers </term> with integral <term> graphics displays </term> offers techniques superior to those
other,55-3-P80-1019,bq these aspects , while still satisfying <term> human communication needs </term> . The paper proposes <term> interfaces
tech,3-4-P80-1019,bq communication needs </term> . The paper proposes <term> interfaces </term> based on a judicious mixture of these
tech,20-4-P80-1019,bq valuable methods of more traditional <term> natural language interfaces </term> . When people use <term> natural language
hide detail