Robust Arabic Text Categorization by Combining Convolutional and Recurrent Neural Networks

Ameur, Mohamed Seghir Hadj; Belkebir, Riadh; Guessoum, Ahmed

doi:10.1145/3390092

Cited by 11 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recurrent Neural Network (RNN) and its different variants are one of the most preferred models by researchers, because of their capability to model complex underlying relationships in sequential data. Mohamed Seghir Hadj Ameur et al 43 have used bi-directional Gated Recurrent Unit (GRU) to learn dependencies between words for extractive text summarization. Qingyu Zhou et al 44 have applied a 2-layer normalized RNN model on vectors encoded (BERT) to extract summary sentences.…”

Section: Literature Reviewmentioning

confidence: 99%

GETS : Sentence Scoring Scheme in Graph-based Extractive Text Summarization for Text Mining Applications

Bhattacharya

Verma

Shir

et al. 2023

Preprint

View full text Add to dashboard Cite

Recently, there is an exponential influx of textual data in big data applications, which necessitates the requirement of text mining tools for analysis of data. In Text Mining applications (TM), Text Summarization (TS) has emerged as an emergent field in Natural Language Processing (NLP). Mostly, in TS, abstractive approaches are presented which build complex models, and thus, a shift is envisioned towards graph-based extractive text summarization models. Such models allow review and feedback analysis of a service or product, and have the benefits of being less complex, flexible, and require low computational resources. This makes them an effective fit for modern text mining based big data and Internet-of-Things (IoT) applications. Thus, in the proposed work, we present a scheme, GETS, which exploits a graph-based model to establish relations between words and sentences based on statistical operations. In the scheme, a post processing phase is presented which uses sentence clustering based on graph preparation. To make the scheme scalable fit for real world applications, we use the Apache Spark environment for parallel execution of graph-based operations. In experimental setup, the Recall-oriented Understudying Gisting Evaluation (ROUGE) parameters is used to evaluate the proposed graph based model with a comparative analysis with ROUGE 1,2,L measures. Comparative analysis is done based on clustered and non-clustered approaches. The obtained results renders the scheme effective as a backend of Artificial Intelligence (AI) models in crowdsourcing applications and decision-analytics models.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

GETS : Sentence Scoring Scheme in Graph-based Extractive Text Summarization for Text Mining Applications

Bhattacharya

Verma

Shir

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recurrent neural network (RNN) and its different variants are one of the most preferred models by researchers because of their capability to model complex underlying relationships in sequential data. Mohamed Seghir Hadj Ameur et al [72] used a bi-directional gated recurrent unit (GRU) to learn dependencies between words for extractive text summarization. Qingyu Zhou et al [73] applied a twolayer normalized RNN model on vectors encoded (BERT) to extract summary sentences, which are also discussed in [74].…”

Section: Literature Reviewmentioning

confidence: 99%

Graph-Based Extractive Text Summarization Sentence Scoring Scheme for Big Data Applications

Verma,

Bhargav,

Bhavsar

et al. 2023

Information

View full text Add to dashboard Cite

The recent advancements in big data and natural language processing (NLP) have necessitated proficient text mining (TM) schemes that can interpret and analyze voluminous textual data. Text summarization (TS) acts as an essential pillar within recommendation engines. Despite the prevalent use of abstractive techniques in TS, an anticipated shift towards a graph-based extractive TS (ETS) scheme is becoming apparent. The models, although simpler and less resource-intensive, are key in assessing reviews and feedback on products or services. Nonetheless, current methodologies have not fully resolved concerns surrounding complexity, adaptability, and computational demands. Thus, we propose our scheme, GETS, utilizing a graph-based model to forge connections among words and sentences through statistical procedures. The structure encompasses a post-processing stage that includes graph-based sentence clustering. Employing the Apache Spark framework, the scheme is designed for parallel execution, making it adaptable to real-world applications. For evaluation, we selected 500 documents from the WikiHow and Opinosis datasets, categorized them into five classes, and applied the recall-oriented understudying gisting evaluation (ROUGE) parameters for comparison with measures ROUGE-1, 2, and L. The results include recall scores of 0.3942, 0.0952, and 0.3436 for ROUGE-1, 2, and L, respectively (when using the clustered approach). Through a juxtaposition with existing models such as BERTEXT (with 3-gram, 4-gram) and MATCHSUM, our scheme has demonstrated notable improvements, substantiating its applicability and effectiveness in real-world scenarios.

show abstract

“…In 2020, Daif et al presented AraDIC [6], the first deep learning framework for Arabic document classification based on image-based characters Ameur et al suggested a hybrid CNN and RNN deep learning model for categorizing Arabic text documents using static, dynamic, and fine-tuned word embedding [3]. The most meaningful representations from the space of Arabic word embedding are automatically learned using a deep learning CNN model.…”

Section: Classificationmentioning

confidence: 99%

“…The Arabic language is the main language of 26 Arab countries (i.e., Arab countries) which possesses many difficulties compared to English. Arabic text analytics are incredibly significant with respect to making our lives easier in many domains such as document text categorization [3], Arabic sentiment analysis [4], and detection of email spam. In fact, the Arabic text faces many challenges as mentioned in [5] such as stemming, dialects, phonology, orthography, and morphology.…”

Section: Introductionmentioning

confidence: 99%

A Novel Deep Learning ArCAR System for Arabic Text Recognition with Character-Level Representation

Muaad

Hanumanthappa

Al-antari

et al. 2021

The 1st International Electronic Conference on Algorithms

View full text Add to dashboard Cite

AI-based text classification is a process to classify Arabic contents into their categories. With the increasing number of Arabic texts in our social life, traditional machine learning approaches are facing different challenges due to the complexity of the morphology and the delicate variation of the Arabic language. This work proposes a model to represent and recognize Arabic text at the character level based on the capability of a deep convolutional neural network (CNN). This system was validated using five-fold cross-validation tests for Arabic text document classification. We have used our proposed system to evaluate Arabic text. The ArCAR system shows its capability to classify Arabic text in character-level. For document classification, the ArCAR system achieves the best performance using the AlKhaleej-balance dataset in terms of accuracy equal to 97.76%. The proposed ArCAR seems to provide a practical solution for accurate Arabic text representation, both for understanding and as a classifications system.

show abstract

Robust Arabic Text Categorization by Combining Convolutional and Recurrent Neural Networks

Cited by 11 publications

References 29 publications

GETS : Sentence Scoring Scheme in Graph-based Extractive Text Summarization for Text Mining Applications

GETS : Sentence Scoring Scheme in Graph-based Extractive Text Summarization for Text Mining Applications

Graph-Based Extractive Text Summarization Sentence Scoring Scheme for Big Data Applications

A Novel Deep Learning ArCAR System for Arabic Text Recognition with Character-Level Representation

Contact Info

Product

Resources

About