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

<div class="floats-full-page floats-full-page-other"><h2>Table 2</h2><div class="floats-full-page-caption"><div>Experimental results for MCTest.</div></div><div class="floats-full-page-content"><table class="fixed-width table-group" id="tab2"><tr><td><table class="table"><colgroup><col style="width:21.55em" /><col style="width:6.01em" /><col style="width:6.14em" /></colgroup><tr><td class="thead-hr" colspan="3"><hr /></td></tr><tr class="thead"><td class="align_left">Method</td><td class="align_center">MC160 Test</td><td class="align_center">MC500 Test</td></tr><tr><td class="thead-hr" colspan="3"><hr /></td></tr><tr><td class="align_left">Richardson et al.(2013)+RTE</td><td class="align_center">0.691</td><td class="align_center">0.633</td></tr><tr><td class="align_left">Sachan et al.(2015)</td><td class="align_center">-</td><td class="align_center">0.678</td></tr><tr><td class="align_left">Wang et al.(2015)</td><td class="align_center">0.753</td><td class="align_center">0.699</td></tr><tr><td class="align_left">Trischler et al.(2016)</td><td class="align_center">0.746</td><td class="align_center">0.710</td></tr><tr><td class="align_left" colspan="3"><hr /></td></tr><tr><td class="align_left">Attentive Reader</td><td class="align_center">0.463</td><td class="align_center">0.419</td></tr><tr><td class="align_left">Neural Reasoner</td><td class="align_center">0.476</td><td class="align_center">0.456</td></tr><tr><td class="align_left">HABCNN-TE</td><td class="align_center">0.631</td><td class="align_center">0.529</td></tr><tr><td class="align_left">Sentence-Level Attention Reader (mode:max+avg)</td><td class="align_center">0.664</td><td class="align_center">0.673</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr" /></td></tr></table></td></tr></table></div></div>

Table 2 | Using Sentence-Level Neural Network Models for Multiple-Choice Reading Comprehension Tasks

title

Table 2: Using Sentence-Level Neural Network Models for Multiple-Choice Reading Comprehension Tasks

description

Table 2

About this journal

<p><em>Wireless Communications and Mobile Computing</em> provides the R&amp;D communities working in academia and the telecommunications and networking industries with a forum for sharing research and ideas in this fast moving field.</p>


Journal profile

Meet the editorial board

<p><em>Wireless Communications and Mobile Computing</em> maintains an Editorial Board of practicing researchers from around the world, to ensure manuscripts are handled by editors who are experts in the field of study.</p>


Editor spotlight

Submit to Special Issue

We currently have a number of Special Issues open for submission. Special Issues highlight emerging areas of research within a field, or provide a venue for a deeper investigation into an existing research area.