Deep Transfer Learning for Question Classification Based on Semantic Information Features of Category Labels

<table class="table-group" id="tab6"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Category label</td><td class="align_center">Before text expansion</td><td class="align_center">After text expansion</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">Relationships</td><td class="align_center">What makes friendship click does spark keep going</td><td class="align_center">What makes friendship click make how does perish make the die spark keep friendly relationship going</td></tr><tr><td class="align_left" colspan="3"><hr/></td></tr><tr><td class="align_left">Computer</td><td class="align_center">How download road runner custom browser software father stubborn call support</td><td class="align_center">Reciprocal comprise how do unregenerate <i>i</i> download road runner hoosier state incorporate custom browser software my father unregenerate in law is stubborn he begetter won <i>t</i> incorporate call comprise support</td></tr><tr><td class="align_left" colspan="3"><hr/></td></tr><tr><td class="align_left">Entertainment</td><td class="align_center">What best old school song ever created must 1994 earlier</td><td class="align_center">What is the mustiness best old school strike rap mustiness song ever created strike civilize must be chance on strike and earlier</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Contrast before and after expansion of the question text.</div>

Computational Intelligence and Neuroscience

tab6

Table 6

Table 6: Deep Transfer Learning for Question Classification Based on Semantic Information Features of Category Labels 