Artificial Intelligence · Natural Language Processing · Scientific Advisory

Murat Can Ganiz, PhD

Associate Professor of Computer Engineering, Marmara University
Founder & Managing Partner, VeriUs Technology

I am a computer scientist, academic researcher, and AI entrepreneur working at the intersection of machine learning, natural language processing, large language models, retrieval-augmented generation, and graph-based reasoning. My research and applied work focus on Turkish NLP, legal AI, healthcare AI, medical information extraction, semantic search, source-grounded conversational AI, and enterprise knowledge systems.

Download CV Google Scholar AVESIS Industrial R&D VeriUs
ResearchAI, machine learning, NLP, LLMs, Graph-RAG, and knowledge-rich reasoning.
Applied AILegal AI, healthcare AI, enterprise document intelligence, and secure domain systems.
Industrial R&DScientific advisory for university-industry collaboration, project design, and AI product strategy.
TeachingUndergraduate and graduate courses in NLP, data science, machine learning, and core CS topics.
Murat Can Ganiz
Researcher, educator, and AI entrepreneur focused on impactful academic and industrial work.

Profile

At Marmara University, I teach and conduct research in artificial intelligence, machine learning, natural language processing, data science, and text mining. At VeriUs Technology, a university spin-off founded in 2013, I lead the development of domain-focused AI products and custom AI systems for law, healthcare, and enterprise document intelligence. I also advise companies on industrial R&D projects, scientific project design, AI product strategy, and university-industry collaborations.

Machine LearningNLPLLMsRAGGraph-RAGLegal AIHealthcare AITurkish NLPData ScienceKnowledge Graphs

Academic Research and Real-World AI

My academic work centers on methods that improve learning, retrieval, and reasoning over complex textual and graph-structured data, especially for Turkish and other low-resource settings.

My applied work turns these ideas into operational systems: domain-adapted RAG pipelines, legal and healthcare AI products, secure enterprise AI deployments, and knowledge-intensive question answering.

Who this site is for: students, collaborators, graduate applicants, industry partners, and companies looking for scientific advisory in AI, NLP, LLMs, RAG, and domain-focused intelligent systems.

Current Focus

  • Large language models, retrieval-augmented generation, Graph-RAG, agentic RAG, and hybrid retrieval architectures.
  • Turkish NLP and low-resource language technologies, including text classification, named entity recognition, information extraction, summarization, semantic search, and consistency analysis of LLM outputs.
  • Legal AI systems for Turkish legislation, case law, contract analysis, case analysis, and source-grounded legal question answering.
  • Healthcare AI and medical NLP, including clinical information extraction, radiology report analysis, cardiological intelligence, and medical Graph-RAG.
  • Enterprise and private document intelligence with secure deployment, data processing pipelines, knowledge-network construction, concept extraction, relation extraction, labeling, and explainability.
  • On-premise and customer-specific AI systems integrating vector databases, search engines, graph databases, domain-adapted models, and evaluation pipelines.

Research

My long-term research interests are in artificial intelligence, machine learning, deep learning, text mining, linked data, graph mining, social network analysis, and distributed data mining. A recurring theme in my work is using semantic and graph-based representations to improve learning from textual data, especially in Turkish and other low-resource settings.

I direct the Big Data and Text Analytics Research Lab at Marmara University. Previously, I directed the Social Network Analysis and Data Mining Research Lab at Doğuş University.

Applied AI and VeriUs Technology

VeriUs Technology develops real-world applications of machine learning, natural language processing, and large language models. Recent work includes domain-focused conversational AI systems and RAG-based products for legal, healthcare, and enterprise knowledge domains.

hukuk.chat

AI-powered legal assistant for Turkish law, supporting source-grounded answers, legislation and case-law retrieval, legal document analysis, contract analysis, and case analysis.

Health Chat / saglik.chat

AI assistant for physicians, medical literature summarization, clinical decision-support interfaces, and medical Graph-RAG components.

Private Document Intelligence

AI-based secure private document search, summarization, analysis, and enterprise knowledge management.

Industrial R&D and Scientific Advisory

Scientific advisory and applied R&D support for companies building AI, NLP, LLM/RAG, legal AI, healthcare AI, and enterprise knowledge systems.

Selected Recent Publications

Full publication lists are available through Google Scholar and AVESIS.

  1. Shaqalaih, L. I. A., Belal, O. S., Küçük, F. M., Tuncer, Y., & Ganiz, M. C. (2025). Medical Graph-RAG: Bilingual Graph-Based Reasoning for Cardiological Intelligence. INISTA 2025. DOI: 10.1109/INISTA68122.2025.11249583.
  2. Abdullahi, A. A., Ganiz, M. C., Koç, U., Gökhan, M. B., Aydın, C., & Özdemir, A. B. (2025). Deep learning for named entity recognition in Turkish radiology reports. Diagnostic and Interventional Radiology, 31(5), 430–439.
  3. Tuncer, Y., Pekedis, H., Özeren, H., & Ganiz, M. C. (2025). New Approaches to Named Entity Recognition in Turkish: Improving Performance through Architecture Modification of Causal Large Language Models. SIU 2025. DOI: 10.1109/SIU66497.2025.11112472.
  4. Üzümcü, T., & Ganiz, M. C. (2025). Analysis of Consistency of Large Language Models for Low-Resource Languages like Turkish with Min-P and Top-P Sampling Parameters. SIU 2025. DOI: 10.1109/SIU66497.2025.11112080.
  5. Mehmetcik, H., Ganiz, M. C., Kölük, M., Yüksel, G., Yılmaz, M., İnce, M. M., et al. (2024). TFPsocialmedia: a public dataset for studying Turkish foreign policy. Discover Data, 2(1), 3.
  6. Alsaç, A., Yenisey, M. M., Ganiz, M. C., Dağtekin, M., & Ulusinan, T. (2023). The Efficiency of Regularization Method on Model Success in Issue Type Prediction Problem. Acta Infologica, 7(2), 360–383.
  7. Akça, O., Bayrak, G., Issifu, A. M., & Ganiz, M. C. (2022). Traditional Machine Learning and Deep Learning-based Text Classification for Turkish Law Documents using Transformers and Domain Adaptation. INISTA 2022.
  8. Çelikmasat, G., Aktürk, M. E., Ertunç, Y. E., Issifu, A. M., & Ganiz, M. C. (2022). Biomedical Named Entity Recognition Using Transformers with biLSTM + CRF and Graph Convolutional Neural Networks. INISTA 2022.
  9. Bayrak, G., Toprak, M. Ş., Ganiz, M. C., Kodaz, H., & Koç, U. (2022). Deep learning-based brain hemorrhage detection in CT reports. Challenges of Trustable AI and Added-Value on Health, 866–867.
  10. Issifu, A. M., & Ganiz, M. C. (2021). A Simple Data Augmentation Method to Improve the Performance of Named Entity Recognition Models in Medical Domain. UBMK 2021.

Teaching and Advising

I have offered undergraduate and graduate courses across natural language processing, machine learning, data science, social network analysis, software design, and core computer engineering topics.

View the dedicated teaching page.

I have supervised graduate theses in legal NLP, medical information extraction, radiology report classification, data augmentation for NLP, financial disclosure analysis, word embeddings, word sense disambiguation, semantic kernels, sentiment analysis, and higher-order semantic smoothing.

Education

Contact

Department of Computer Engineering
Faculty of Engineering, Marmara University
RTE Campus, Maltepe, Istanbul, Türkiye

Office: M2-251
Big Data and Text Analytics Research Lab: M2-118

E-mail: murat.ganiz@marmara.edu.tr
Phone: +90 216 777 3539

LinkedIn · Google Scholar · AVESIS · VeriUs Technology