Research Interests

The research group focuses on the intersection of machine learning techniques with the areas of Natural Language Processing (NLP) and Computer Vision. Their primary research interests include:

1. Natural Language Processing (NLP)

Solutions for the Arabic Languae
Sentiment analysis: Analyzing and understanding the sentiment expressed in textual data.
Named Entity Recognition (NER): Identifying and categorizing entities (e.g., names, organizations, locations) in text.
Text classification: Categorizing and organizing text into predefined classes or topics.
Machine translation: Developing algorithms for automated translation between languages.
Text generation: Creating coherent and contextually appropriate text using generative models.
Question-Answering Systems: Building systems that can understand and respond to questions posed in natural language.

2. Computer Vision

Medical Solutions
Object detection: Locating and classifying objects within images or video frames.
Image segmentation: Partitioning images into meaningful segments for further analysis.
Image captioning: Generating textual descriptions of the content present in images.
Facial recognition: Developing systems capable of recognizing and verifying individuals from facial images or video streams.
Visual sentiment analysis: Determining the sentiment or emotions portrayed in images or videos.
Action recognition: Identifying and understanding human actions from video data.

4. Transfer learning and pre-trained models

Leveraging pre-trained models, such as BERT, GPT, or vision-based models like ResNet, to boost performance in specific NLP and computer vision tasks.
Adapting models across related domains to save computation and training time.

The research group actively collaborates with other researchers and institutions to push the boundaries of knowledge in machine learning, NLP, and computer vision, with a strong emphasis on real-world applications.

Trending

Interview with Jordanian Academy of Arabic Language Radio

The Group Gets a Grant from SRISF

Research Interests