A Multilingual Encoding Method for Text Classification and Dialect Identification Using Convolutional Neural Network
This work addresses text classification and dialect identification for multilingual applications, but it appears incremental as it builds on existing CNN and hybrid word-character approaches.
The authors tackled text classification and dialect identification by introducing a language-independent model with new encoding methods (BUNOW and BUNOC) and a CNN spatial architecture, achieving promising results compared to state-of-the-art models on Arabic and English datasets.
This thesis presents a language-independent text classification model by introduced two new encoding methods "BUNOW" and "BUNOC" used for feeding the raw text data into a new CNN spatial architecture with vertical and horizontal convolutional process instead of commonly used methods like one hot vector or word representation (i.e. word2vec) with temporal CNN architecture. The proposed model can be classified as hybrid word-character model in its work methodology because it consumes less memory space by using a fewer neural network parameters as in character level representation, in addition to providing much faster computations with fewer network layers depth, as in word level representation. A promising result achieved compared to state of art models in two different morphological benchmarked dataset one for Arabic language and one for English language.