A Two-Step Neural Dialog State Tracker for Task-Oriented Dialog Processing

<table class="table-group" id="tab10"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Model</td><td class="align_center">Accuracy</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">NT-Atten-NoHier</td><td class="align_center">0.0672</td></tr><tr><td class="align_left">NT-NoAtten-Hier</td><td class="align_center">0.0422</td></tr><tr><td class="align_left"><i>NT-Atten-Hier</i></td><td class="align_center"><b>0.0697</b></td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The dialog state tracking accuracy of the proposed model’s variants.</div>

Computational Intelligence and Neuroscience

tab10

Table 10

Table 10: A Two-Step Neural Dialog State Tracker for Task-Oriented Dialog Processing 