Classifying educational materials in low-resource languages
Gihad N. Sohsah, Onur Güzey, Tarmanini Zaina · Istanbul Şehir University Institutional Repository (Istanbul Şehir University) · 2016
Classifyingeducationalresourcessuchasvideosandarticles can be challenging in low-resource languages due to lack of appropriate tools and sufficient labeled data. To overcomethisproblem,acrosslingualclassificationmethod that utilizes resources created in one high-resource language, such as English, to perform classification in many low-resource languages, is proposed. Data scarcity issue is prevented by transferring information from highresources languages to the low-resources ones. First, word embeddings are extracted using one of the frameworks proposedpreviously,thenclassifiersaretrainedusingthehighresource language documents. Two versions of the method thatusedifferenthigher-levelcompositionfunctionsareimplemented and compared.