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

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Parameter</td><td class="align_center">Value</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Embedding size</td><td class="align_center">500</td></tr><tr><td class="align_left">Filter sizes</td><td class="align_center">2, 3, 4</td></tr><tr><td class="align_left">The number of filters</td><td class="align_center">128</td></tr><tr><td class="align_left">Dropout ratio</td><td class="align_center">0.5</td></tr><tr><td class="align_left">Batch size</td><td class="align_center">50</td></tr><tr><td class="align_left">Number of epochs</td><td class="align_center">1,000</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The parameters for the informativeness classifier and their values.</div>

Computational Intelligence and Neuroscience

tab4

Table 4

Table 4: A Two-Step Neural Dialog State Tracker for Task-Oriented Dialog Processing 