Learning to Identify Arabic and German Dialects using Multiple Kernels

Abstract

We present a machine learning approach for the Arabic Dialect Identification (ADI) and the German Dialect Identification (GDI) Closed Shared Tasks of the DSL 2017 Challenge. The proposed approach combines several kernels using multiple kernel learning. While most of our kernels are based on character p-grams (also known as n-grams) extracted from speech transcripts, we also use a kernel based on i-vectors, a low-dimensional representation of audio recordings, provided only for the Arabic data. In the learning stage, we independently employ Kernel Discriminant Analysis (KDA) and Kernel Ridge Regression (KRR). Our approach is shallow and simple, but the empirical results obtained in the shared tasks prove that it achieves very good results. Indeed, we ranked on the first place in the ADI Shared Task with a weighted F 1 score of 76.32% (4.62% above the second place) and on the fifth place in the GDI Shared Task with a weighted F 1 score of 63.67% (2.57% below the first place).

Transductive Learning with String Kernels for Cross-Domain Text Classification

“…Remarkably, they obtain state-of-the-art performance without using knowledge from the target domain, which indicates that string kernels provide robust results in the cross-domain setting without any domain adaptation. Ionescu et al [18] obtained the best performance in the Arabic Dialect Identification Shared Task of the 2017 VarDial Evaluation Campaign [41], with an improvement of 4.6% over the second-best method. It is important to note that the training and the test speech samples prepared for the shared task were recorded in different setups [41], or in other words, the training and the test sets are drawn from different distributions.…”

“…However, researchers proposed several domain adaptation techniques by using the unlabeled test data to obtain better performance [5,14,16,25,37]. Interestingly, some recent works [13,18] indicate that string kernels can yield robust results in the cross-domain setting without any domain adaptation. In fact, methods based on string kernels have demonstrated impressive results in various text classification tasks ranging from native language identification [22][23][24]36] and authorship identification [34] to dialect identification [4,18,21], sentiment analysis [13,35] and automatic essay scoring [7].…”

Language model adaptation for language and dialect identification of text

“…Team qcri mit used an ensemble of two SVMs and a stochastic gradient classifier (SGD). Team unibuckernel experimented with different kernels using kernel ridge regression (KRR) and kernel discriminant analysis (KDA) (Ionescu & Butnaru, 2017). They obtained their best results using KRR based on the sum of three kernels.…”

Local frame match distance: A novel approach for exemplar gesture recognition

“…Our algorithm is inspired by LRD [9] which has successfully been applied to phylogenetic analysis [9], sequence alignment [10], native language identification [11], [12], [13] and Arabic dialect identification [14], [32]. We next present how we adapt LRD and obtain a novel algorithm, termed Local Frame Match Distance, for the task of gesture recognition.…”