refuted by noone ( e.g. , I walked is to to walk as I laughed is to to laugh , noted
, <term> communication </term> . Our goal is to recognize and isolate such <term> miscommunications
</term> of <term> human language learners </term> , to the <term> output </term> of <term> machine translation
HDAGs </term> . We applied the proposed method to <term> question classification </term> and <term>
predicting top-level topic shifts </term> to the problem of <term> identifying subtopic
For many reasons , it is highly desirable to accurately estimate the <term> confidence
can converse with their logistics system to place a supply or information request .
two <term> formalisms </term> . We then turn to a discussion comparing the <term> linguistic
domains </term> . This workshop is intended to give an introduction to <term> statistical
complete and correct interpretations has to be abandoned . However , our experience
<term> computational linguists </term> seem to be quite dubious about <term> analogies between
utilizes <term> typed feature structures </term> to control the <term> top-down derivation </term>
the <term> accuracy rate </term> directly . To make the proposed algorithm robust , the
these <term> indices </term> can be obtained . To support engaging human users in robust
This process enables the <term> system </term> to understand <term> user utterances </term> based
seemed more important to devise methods to grasp the <term> global meaning </term> of
require a <term> pre-tagged corpus </term> to fit . One of the distinguishing features
focusing especially on the changes made to the <term> SUMMIT recognizer </term> . These
</term> . We demonstrate that it is feasible to create <term> training material </term> for
</term> : they would not be enough numerous to be of any use . We report experiments conducted
hide detail