Dual-Level Attention Based on a Heterogeneous Graph Convolution Network for Aspect-Based Sentiment Classification

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="1"><hr/></td></tr><tr><td class="align_center">Entity labels</td></tr><tr><td class="align_left">Restaurant, food, drinks, ambience, service, location</td></tr><tr><td class="align_center">Attribute labels</td></tr><tr><td class="align_left">General, prices, quality, style_options, miscellaneous</td></tr><tr class="table-tr"><td colspan="1"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The entity and attribute of datasets.</div>

Wireless Communications and Mobile Computing

tab2

Table 2

Table 2: Dual-Level Attention Based on a Heterogeneous Graph Convolution Network for Aspect-Based Sentiment Classification 