Research in an academic environment provides a unique opportunity to solve problems and vision the technology of the future. During my study as a bachelor, master, PhD student, research assistant, post-doc researcher and senior researcher, I have found that the ability to connect real-world applications with theoretical models is crucial to successful research. This includes abstracting a problem to its essence and then devising effective techniques for its solution. In my experience, many different problems, share some common characteristics. Understanding these inherent characteristics has enabled us to tackle problems at deeper levels and enables us to develop better solutions.
Machin learning and Deep Learning-based method —Artificial Intelligence (AI) is a branch of computer science where the idea is to simulate the human brain. In other words, it is a method to do a task that is potentially easy for humans, but difficult for the machines. Machine learning (ML) is a subclass of artificial intelligence. Its main task is to extract key features from data to cope with complex problems and handle large collections of data. Deep Learning is a new area of Machine Learning research, which has been introduced to move Machine Learning closer to one of its original goals: Artificial Intelligence. Learning can be supervised, semi-supervised or unsupervised.
Text data is becoming ubiquitous in all segments of life. On the other hands, a huge amount of text data are generated every day using apps messages, social media, forums, news publishing platforms and many other channels. Therefore, because of the large volumes of text data as well as the highly unstructured data source, NLP can be applied to handle large volumes of text data and structure highly unstructured data source.
Natural Language Processing (NLP) — is a field that combines linguistics, cognitive science, statistical machine learning and other computer science areas to compile intelligent computer systems that can understand human languages. NLP has various applications, among which are text similarity, question answering, sentiment analysis, automatic summarization, search engines, etc. Furthermore, there are different level of natural language: morphological, lexical, pragmatic, phonology, semantic, syntactic, discourse. Moreover, there are various approaches to NLP such as symbolic, statistical, connectionist, rule-based, knowledge-based and machine learning-based. Also, there are several open sources NLP that are used for fundamental NLP tasks, such as syntactic parsing, part-of-speech (POS) tagging, named entity recognition (NER), etc.
In particular, my research interests in computer science include:
• Artificial intelligence, Machine learning and Deep Learning.
• Text mining, Natural Language Processing (NLP),
• Data mining
The central focus of my research is to bring together all areas above and design methods/algorithms for various problems on text data mining. Over the last decade, I contributed to a wide range of topics in NLP. Meanwhile, I enjoy collaborating with scientists and domain experts of different background for interdisciplinary research in data science.
Research accomplishments — over the past years, my research interests and contributions cover different aspects of NLP and data mining, as demonstrated below:
1) Natural Language Processing (NLP) and Artificial intelligence
2) Deep Learning and machine learning for Natural Language Processing
3) Artificial Intelligence approach to Data Science
Abdi, A. and N. Idris (2014). Automated summarization assessment system: quality assessment without a reference summary. The International Conference on Advances in Applied Science and Environmental Engineering-ASEE.
Abdi, S. A. and N. Idris (2014). "An analysis on student-written summaries: automatic assessment of summary writing." International Journal of Enhanced Research in Science Technology & Engineering 3: 466-472.
Abdi, A. "Interactive English Natural Language Interface to Generate SQL Query", DOI: https://doi.org/10.1115/1.859940.paper6
Google Scholar Link