Using Sentence-Level Neural Network Models for Multiple-Choice Reading Comprehension Tasks

<table class="fixed-width table-group" id="tab1"><tr><td><table class="table"><colgroup><col style="width:6.24em"/><col style="width:5.95em"/><col style="width:5.21em"/><col style="width:4.28em"/></colgroup><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left"> </td><td class="align_center">Documents</td><td class="align_center">Sentences</td><td class="align_center">options</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Train</td><td class="align_center">769</td><td class="align_center">28235</td><td class="align_center">3845</td></tr><tr><td class="align_left">BCEETest</td><td class="align_center">13</td><td class="align_center">548</td><td class="align_center">65</td></tr><tr><td class="align_left">SBCEETest1</td><td class="align_center">12</td><td class="align_center">517</td><td class="align_center">60</td></tr><tr><td class="align_left">SBCEETest2</td><td class="align_center">52</td><td class="align_center">2056</td><td class="align_center">260</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Statistics of multiple-choice reading comprehension datasets: train and three tests.</div>

Wireless Communications and Mobile Computing

tab1

Table 1

Table 1: Using Sentence-Level Neural Network Models for Multiple-Choice Reading Comprehension Tasks 