Mounir Zrigui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mounir Zrigui has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Henri Nicolas
Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800
8 shared publications - Mohsen Maraoui
UTIC Laboratory University of Monastir Tunisia
8 shared publications - Manar Joundy Hazar
University of Al-Qadisiyah
7 shared publications - Samawel Jaballi
Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800
6 shared publications - Anis Zouaghi
Gabès University
5 shared publications - Bassem Bsir
University of Monastir
5 shared publications
Latest Publications
- 21 September 2026
- Published by Springer Nature
- p. 362-375
When Silence Matters: How VAD-Driven Whisper Architectures Reshape Temporal Alignment in Low-Resource Multilingual ASR
- 21 September 2026
- Published by Springer Nature
- p. 362-375
When Silence Matters: How VAD-Driven Whisper Architectures Reshape Temporal Alignment in Low-Resource Multilingual ASR
- 1 June 2026
- Published by Springer Nature
- p. 449-460
Advancing Arabic Named Entity Recognition in Invoices with YOLOv11, BERT, Active Learning, and LLM Integration
- 1 June 2026
- Published by Springer Nature
- p. 449-460
Advancing Arabic Named Entity Recognition in Invoices with YOLOv11, BERT, Active Learning, and LLM Integration
- 8 November 2025
- Published by Springer Nature
- p. 155-169
Classification of Violent Scenes in Cartoon Videos Using Deep Learning Techniques
- 8 November 2025
- Published by Springer Nature
- p. 155-169
Classification of Violent Scenes in Cartoon Videos Using Deep Learning Techniques
- 8 November 2025
- Published by Springer Nature
- p. 170-183
Real-Time Automated Detection of Violent Content in Animated Cartoons Using YOLO
- 8 November 2025
- Published by Springer Nature
- p. 170-183
Real-Time Automated Detection of Violent Content in Animated Cartoons Using YOLO
- Open Access
- 1 January 2025
- Published by Springer Nature in Research Square
A Hybrid E-Learning Recommendation System Incorporating User Reviews and Ratings for Enhanced Course Selection
A recommendation system can be used in E-learning to suggest relevant and personalized resources. It uses data about learners' behaviors, such as the courses they have taken, the content they have viewed, and the assessments they have completed, to make recommendations for additional learning opportunities. In this work, we build a hybrid educational video recommender system based on learners’ reviews and ratings. We use a Latent Dirichlet Allocation (LDA) topic model on textual data extracted from educational videos to train language models as an input to a supervised Convolutional Neural Network (CNN) model. Additionally, we use a Latent Factor Model (LFM) to extract educational video features and learners' preferences from their historical data (ratings and reviews) as an output CNN model. In our proposed technique, we use hybrid user ratings and reviews to tackle sparsity and cold start problems in the recommender system. Our recommender uses reviews to predict a new sentiment matrix. For cases where reviews are absent (represented as empty cells in the sentiment matrix) or comments are ambiguous, the system utilizes normalized user ratings from the rating matrix, employing a tailored mathematical framework specifically designed for this purpose.
- 1 January 2025
- Published by Springer Nature in Research Square
Open AccessA Hybrid E-Learning Recommendation System Incorporating User Reviews and Ratings for Enhanced Course Selection
A recommendation system can be used in E-learning to suggest relevant and personalized resources. It uses data about learners' behaviors, such as the courses they have taken, the content they have viewed, and the assessments they have completed, to make recommendations for additional learning opportunities. In this work, we build a hybrid educational video recommender system based on learners’ reviews and ratings. We use a Latent Dirichlet Allocation (LDA) topic model on textual data extracted from educational videos to train language models as an input to a supervised Convolutional Neural Network (CNN) model. Additionally, we use a Latent Factor Model (LFM) to extract educational video features and learners' preferences from their historical data (ratings and reviews) as an output CNN model. In our proposed technique, we use hybrid user ratings and reviews to tackle sparsity and cold start problems in the recommender system. Our recommender uses reviews to predict a new sentiment matrix. For cases where reviews are absent (represented as empty cells in the sentiment matrix) or comments are ambiguous, the system utilizes normalized user ratings from the rating matrix, employing a tailored mathematical framework specifically designed for this purpose.
- Open Access
- 27 November 2024
- Published by Springer Nature in Research Square
Leveraging Large Language Models to Build a Cutting-Edge French Word Sense Disambiguation Corpus
With the increasing amount of data circulating over the Web, there is a growing need to develop and deploy tools aimed at unraveling semantic nuances within text or sentences. The challenges in extracting precise meanings arise from the complexity of natural language, while words usually have multiple interpretations depending on the context. The challenge of precisely interpreting words within a given context is what the task of Word Sense Disambiguation meets. It is a very old domain within the area of Natural Language Processing aimed at determining a word’s meaning that it is going to carry in a particular context, hence increasing the correctness of applications processing the language. Numerous linguistic resources are accessible online, including WordNet [1], thesauri[2], and dictionaries, enabling exploration of diverse contextual meanings. However, several limitations persist. These include the scarcity of resources for certain languages, a limited number of examples within corpora, and the challenge of accurately detecting the topic or context covered by text, which significantly impacts word sense disambiguation.This paper will discuss the different approaches to WSD and review corpora available for this task. We will contrast these approaches, highlighting the limitations, which will allow us to build a corpus in French, targeted for WSD.
- 27 November 2024
- Published by Springer Nature in Research Square
Open AccessLeveraging Large Language Models to Build a Cutting-Edge French Word Sense Disambiguation Corpus
With the increasing amount of data circulating over the Web, there is a growing need to develop and deploy tools aimed at unraveling semantic nuances within text or sentences. The challenges in extracting precise meanings arise from the complexity of natural language, while words usually have multiple interpretations depending on the context. The challenge of precisely interpreting words within a given context is what the task of Word Sense Disambiguation meets. It is a very old domain within the area of Natural Language Processing aimed at determining a word’s meaning that it is going to carry in a particular context, hence increasing the correctness of applications processing the language. Numerous linguistic resources are accessible online, including WordNet [1], thesauri[2], and dictionaries, enabling exploration of diverse contextual meanings. However, several limitations persist. These include the scarcity of resources for certain languages, a limited number of examples within corpora, and the challenge of accurately detecting the topic or context covered by text, which significantly impacts word sense disambiguation.This paper will discuss the different approaches to WSD and review corpora available for this task. We will contrast these approaches, highlighting the limitations, which will allow us to build a corpus in French, targeted for WSD.
- 25 July 2024
- Published by Springer Nature
- p. 380-388
Deep Learning Based Transformers for Keyword Extraction
- 25 July 2024
- Published by Springer Nature
- p. 380-388
Deep Learning Based Transformers for Keyword Extraction
- 16 July 2024
- Published by Springer Nature
- p. 97-107
Oral Diseases Recognition Based on Photographic Images and Dental Decay Diagnosis
- 16 July 2024
- Published by Springer Nature
- p. 97-107
Oral Diseases Recognition Based on Photographic Images and Dental Decay Diagnosis