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

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Set</td><td class="align_center">Informative</td><td class="align_center">Noninformative</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">Training</td><td class="align_center">9,974</td><td class="align_center">2,785</td></tr><tr><td class="align_left">Development</td><td class="align_center">4,139</td><td class="align_center">673</td></tr><tr><td class="align_left">Test</td><td class="align_center">6,528</td><td class="align_center">1,320</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The class distribution for the informativeness classifier.</div>

Computational Intelligence and Neuroscience

tab2

Table 2

Table 2: A Two-Step Neural Dialog State Tracker for Task-Oriented Dialog Processing 