A Proposed Approach for Arabic Language Segmentation

Souri, Adnan; Achhab, Mohammed Al; Mouhajir, Badr Eddine El

doi:10.1109/acling.2015.13

Cited by 5 publications

(11 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the work presented in this paper involves as continuity to our previous work dealing with Recurrent Neural Networks application on Arabic language. In [3], we assumed that Arabic scripts have numerous challenges associated such as (1) the variant shape of letters depending on their position in a word, (2) the problem of writing units, (3) the length of sentences due to little use of punctuation marks, (4) the lack of space between sentence components in usual cases, and (5) the lack of vowelization. For this, it involves being harder to deal with Arabic script.…”

Section: Related Workmentioning

confidence: 99%

“…For this, it involves being harder to deal with Arabic script. Therefore, by keeping in view these features in Arabic script, we have used our segmentation method proposed in [3]. The segmentation method helps in partitioning text into units that will be converted in a next step into vectors (numerical representations) that will serve as input to the CNN model.…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, Arabic information amount in the Web is growing daily. However, Arabic language still suffers from a lot of lack in the field of Natural Language Processing (NLP) [3,4]. For these reasons, it can be said that Arabic language is in the top interests of NLP research domains [1].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural network dealing with Arabic language

Souri

Achhab

Elmohajir

et al. 2020

IJ-ICT

Self Cite

View full text Add to dashboard Cite

Artificial Neural Networks have proved their efficiency in a large number of research domains. In this paper, we have applied Artificial Neural Networks on Arabic text to prove correct language modeling, text generation, and missing text prediction. In one hand, we have adapted Recurrent Neural Networks architectures to model Arabic language in order to generate correct Arabic sequences. In the other hand, Convolutional Neural Networks have been parameterized, basing on some specific features of Arabic, to predict missing text in Arabic documents. We have demonstrated the power of our adapted models in generating and predicting correct Arabic text comparing to the standard model. The model had been trained and tested on known free Arabic datasets. Results have been promising with sufficient accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Neural network dealing with Arabic language

Souri

Achhab

Elmohajir

et al. 2020

IJ-ICT

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, the work presented in this paper involves as a continuity to our previous work dealing with Recurrent Neural Networks application on Arabic language, Arabic text segmentation and a study about Arabic datasets and corpora. In [11], we assumed that Arabic scripts has numerous challenges associated. We mention here the variant shape of letters depending on their position in a word, the problem of writing units, the length of sentences due to little use of punctuation marks, the lack of space between sentence components in usual cases, and the lack of vowelization.…”

Section: Related Workmentioning

confidence: 99%

“…For these reasons and more others, it involves being harder to segment Arabic script with automated tools. Therefore, by keeping in view these features in Arabic script, we have used our segmentation method proposed in [11] basing on what we hav called writing units. The segmentation method helps in partitioning text into units that will be converted in a next step into vectors (numerical representations) that will serve as input to the CNN model.…”

Section: Related Workmentioning

confidence: 99%

Convolutional Neural Networks in Predicting Missing Text in Arabic

Souri¹,

Zbakh²,

Alachhab³

et al. 2019

IJACSA

Self Cite

View full text Add to dashboard Cite

Missing text prediction is one of the major concerns of Natural Language Processing deep learning community's attention. However, the majority of text prediction related research is performed in other languages but not Arabic. In this paper, we take a first step in training a deep learning language model on Arabic language. Our contribution is the prediction of missing text from text documents while applying Convolutional Neural Networks (CNN) on Arabic Language Models. We have built CNN-based Language Models responding to specific settings in relation with Arabic language. We have prepared our dataset of a large quantity of text documents freely downloaded from Arab World Books, Hindawi foundation, and Shamela datasets. To calculate the accuracy of prediction, we have compared documents with complete text and same documents with missing text. We realized training, validation and test steps at three different stages aiming to increase the performance of prediction. The model had been trained at first stage on documents of the same author, then at the second stage, it had been trained on documents of the same dataset, and finally, at the third stage, the model had been trained on all document confused. Steps of training, validation and test have been repeated many times by changing each time the author, dataset, and the combination author-dataset, respectively. Also we have used the technique of enlarging training data by feeding the CNN-model each time by a larger quantity of text. The model gave a high performance of Arabic text prediction using Convolutional Neural Networks with an accuracy that have reached 97.8% in best case.

show abstract