Improving Loanword Identification in Low-Resource Language with Data Augmentation and Multiple Feature Fusion

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr class="thead"><td class="align_left">Lang</td><td class="align_center">Arabic</td><td class="align_center">Chinese</td><td class="align_center">Russian</td><td class="align_center">Turkish</td></tr><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr><td class="align_left">Size</td><td class="align_center">302, 480</td><td class="align_center">325, 790</td><td class="align_center">314, 208</td><td class="align_center">336, 852</td></tr><tr class="table-tr"><td colspan="5"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Size of training data generated in data augmentation (Uyghur sentences).</div>

Computational Intelligence and Neuroscience

tab4

Table 4

Table 4: Improving Loanword Identification in Low-Resource Language with Data Augmentation and Multiple Feature Fusion 