20 December 2020 in EDUMATIC: Jurnal Pendidikan Informatika
Name disambiguation is the problem solving process to find similar names in sentences. The ambiguity of names can be found in hadith of Sahih Bukhari, names "Abdullah bin Amru" in hadiths no 27 and “Abdullah bin Amru” in hadith no 58, These names are the same, but there is no proof they are the same person. This problem is the early indication of ambiguity of name in the hadith. Based in this problem, this research aims to find name disambiguation of hadith narrators with classification by considering the perawi chain. To solved this problem the authors used Word Sense Disambiguation (WSD), WSD is a process to assign the same meaning from the sentences, based on the context in which the word appears. To classify several names in the hadith, the authors used KNN algorithm, by combining the WSD and KNN method can reduce the ambiguity of names in hadith. The data used in this study came from the hadith of Sahih Bukhori through the pre-processing stage. After conducting the research showed a collection of hadith numbers with the same name prediction with an accuracy of 99% at k = 1. Thus, this method can be used for name disambiguation.
11 August 2020 in IEEE Access
An n-gram syllabification model generally produces a high error rate for a low-resource language, such as Indonesian, because of the high rate of out-of-vocabulary (OOV) n-grams. In this paper, a combination of three methods of data augmentations is proposed to solve the problem, namely swapping consonant-graphemes, flipping onsets, and transposing nuclei. An investigation on 50k Indonesian words shows that the combination of three data augmentation methods drastically increases the amount of both unigrams and bigrams. A previous procedure of flipping onsets has been proven to enhance the standard bigram-syllabification by relatively decreasing the syllable error rate (SER) by up to 18.02%. Meanwhile, the previous swapping consonant-graphemes has been proven to give a relative decrement of SER up to 31.39%. In this research, a new transposing nuclei-based augmentation method is proposed and combined with both flipping and swapping procedures to tackle the drawback of bigram syllabification in handling the OOV bigrams. An evaluation based on k-fold cross-validation (k-FCV), using k = 5, for 50 thousand Indonesian formal words concludes that the proposed combination of the three procedures relatively decreases the mean SER produced by the standard bigram model by up to 37.63%. The proposed model is comparable to the fuzzy k-nearest neighbor in every class (FkNNC)-based model. It is worse than the state-of-the-art model, which is developed using a combination of bidirectional long short-term memory (BiLSTM), convolutional neural networks (CNN), and conditional random fields (CRF), but it offers a low complexity.
20 June 2020 in EDUMATIC: Jurnal Pendidikan Informatika