Enhancement of Target-Oriented Opinion Words Extraction with Multiview-Trained Machine Reading Comprehension Model

<table class="table-group" id="tab1"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left" colspan="2"><b>Review</b>: the operating system and user interface is very intuitive, and the large multitouch track pad is amazing.</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left"><b>Targets</b></td><td class="align_center">Operating system, user interface, multi-touch track pad</td></tr><tr><td class="align_left"><b>Opinions</b></td><td class="align_center">Intuitive, amazing</td></tr><tr><td class="align_left" rowspan="3"><b>Pairs</b></td><td class="align_center">Operating system, intuitive</td></tr><tr><td class="align_center">User interface, intuitive</td></tr><tr><td class="align_center">Multitouch track pad, amazing</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr><tr class="table-fn"><td><div>Targets are marked in Bold and corresponding opinions are in italics.<br/></div></td></tr></table>

<div>Examples for opinion-targets pairs.</div>

Computational Intelligence and Neuroscience

tab1

Table 1

Table 1: Enhancement of Target-Oriented Opinion Words Extraction with Multiview-Trained Machine Reading Comprehension Model 