Search

Classification algorithms have shown exceptional prediction results in the supervised learning area. These classification algorithms are not always efficient when it comes to real-life datasets due to class distributions. As a result, datasets for real-life applications are generally imbalanced. Several methods have been proposed to solve the problem of class imbalance. In this paper, we propose a hybrid method combining the preprocessing techniques and those of ensemble learning. The original training set is undersampled by evaluating the samples by stochastic measurement (SM) and then training these samples selected by Multilayer Perceptron to return a balanced training set. The MLPUS (Multilayer perceptron undersampling) balanced training set is aggregated using the bagging ensemble method. We applied our method to the real-life Niger_Rice dataset and forty-four other imbalanced datasets from the KEEL repository in this study. We also compared our method with six other existing methods in the literature, such as the MLP classifier on the original imbalance dataset, MLPUS, UnderBagging (combining random under-sampling and bagging), RUSBoost, SMOTEBagging (Synthetic Minority Oversampling Technique and bagging), SMOTEBoost. The results show that our method is competitive compared to other methods. The Niger_Rice real-life dataset results are 75.6, 0.73, 0.76, and 0.86, respectively, for accuracy, F-measure, G-mean, and ROC with our proposed method. In contrast, the MLP classifier on the original imbalance Niger_Rice dataset gives results 72.44, 0.82, 0.59, and 0.76 respectively for accuracy, F-measure, G-mean, and ROC.

Out-of-vocabulary (OOV) words are the most challenging problem in automatic speech recognition (ASR), especially for morphologically rich languages. Most end-to-end speech recognition systems are performed at word and character levels of a language. Amharic is a poorly resourced but morphologically rich language. This paper proposes hybrid connectionist temporal classification with attention end-to-end architecture and a syllabification algorithm for Amharic automatic speech recognition system (AASR) using its phoneme-based subword units. This algorithm helps to insert the epithetic vowel እ[ɨ], which is not included in our Grapheme-to-Phoneme (G2P) conversion algorithm developed using consonant–vowel (CV) representations of Amharic graphemes. The proposed end-to-end model was trained in various Amharic subwords, namely characters, phonemes, character-based subwords, and phoneme-based subwords generated by the byte-pair-encoding (BPE) segmentation algorithm. Experimental results showed that context-dependent phoneme-based subwords tend to result in more accurate speech recognition systems than the character-based, phoneme-based, and character-based subword counterparts. Further improvement was also obtained in proposed phoneme-based subwords with the syllabification algorithm and SpecAugment data augmentation technique. The word error rate (WER) reduction was 18.38% compared to character-based acoustic modeling with the word-based recurrent neural network language modeling (RNNLM) baseline. These phoneme-based subword models are also useful to improve machine and speech translation tasks.

This article studies convolutional neural networks for Tigrinya (also referred to as Tigrigna), which is a family of Semitic languages spoken in Eritrea and northern Ethiopia. Tigrinya is a “low-resource” language and is notable in terms of the absence of comprehensive and free data. Furthermore, it is characterized as one of the most semantically and syntactically complex languages in the world, similar to other Semitic languages. To the best of our knowledge, no previous research has been conducted on the state-of-the-art embedding technique that is shown here. We investigate which word representation methods perform better in terms of learning for single-label text classification problems, which are common when dealing with morphologically rich and complex languages. Manually annotated datasets are used here, where one contains 30,000 Tigrinya news texts from various sources with six categories of “sport”, “agriculture”, “politics”, “religion”, “education”, and “health” and one unannotated corpus that contains more than six million words. In this paper, we explore pretrained word embedding architectures using various convolutional neural networks (CNNs) to predict class labels. We construct a CNN with a continuous bag-of-words (CBOW) method, a CNN with a skip-gram method, and CNNs with and without word2vec and FastText to evaluate Tigrinya news articles. We also compare the CNN results with traditional machine learning models and evaluate the results in terms of the accuracy, precision, recall, and F1 scoring techniques. The CBOW CNN with word2vec achieves the best accuracy with 93.41%, significantly improving the accuracy for Tigrinya news classification.