tech,3-1-H01-1055,ak in new domains . Recent advances in <term> Automatic Speech Recognition technology </term> have put the goal of naturally sounding
tech,14-1-H01-1055,ak put the goal of naturally sounding <term> dialog systems </term> within reach . However , the improved
tech,4-2-H01-1055,ak within reach . However , the improved <term> speech recognition </term> has brought to light a new problem
tech,15-2-H01-1055,ak brought to light a new problem : as <term> dialog systems </term> understand more of what the <term>
other,22-2-H01-1055,ak </term> understand more of what the <term> user </term> tells them , they need to be more
other,36-2-H01-1055,ak sophisticated at responding to the <term> user </term> . The issue of <term> system response
other,3-3-H01-1055,ak the <term> user </term> . The issue of <term> system response </term> to <term> users </term> has been extensively
other,6-3-H01-1055,ak issue of <term> system response </term> to <term> users </term> has been extensively studied by the
other,13-3-H01-1055,ak has been extensively studied by the <term> natural language generation community </term> , though rarely in the context of
tech,24-3-H01-1055,ak </term> , though rarely in the context of <term> dialog systems </term> . We show how research in <term> generation
tech,5-4-H01-1055,ak systems </term> . We show how research in <term> generation </term> can be adapted to <term> dialog systems
tech,10-4-H01-1055,ak generation </term> can be adapted to <term> dialog systems </term> , and how the high cost of hand-crafting
tech,20-4-H01-1055,ak how the high cost of hand-crafting <term> knowledge-based generation systems </term> can be overcome by employing <term>
tech,28-4-H01-1055,ak </term> can be overcome by employing <term> machine learning techniques </term> . In this paper , we address the
skrij podrobnosti