Artificial Intelligence and Innovation Centre (AIIC)
Research Areas
The AIIC specializes in interdisciplinary research, addressing key sectors such as healthcare, business, and engineering. We develop tools ranging from predictive analytics and automation systems to intelligent software solutions. Additionally, we explore video game development, creating immersive gameplay experiences. A significant effort is also dedicated to the digital enhancement of the Kurdish language, with ongoing work in natural language processing, machine translation, and voice recognition to ensure its inclusion in the global digital landscape.
Education and Training
- The AIIC supports skill development through various programs, including workshops, training sessions, and internships.
- Programs are designed for students, researchers, and professionals seeking practical experience in AI, data science, and video game development.
- Participants gain access to modern tools and expert guidance to help them contribute to innovation across multiple fields.
Events and Highlights
- The AIIC will host conferences, guest lectures, and training sessions to promote collaboration and knowledge-sharing.
- Provides opportunities for networking, learning, and exploring advancements in AI research and technology.
- Offers a range of events, from beginner-friendly workshops to advanced technical seminars, catering to diverse levels of expertise.
Publications and Knowledge Hub
AIIC serves as a resource for knowledge and innovation by publishing its research findings, technical reports, and project outcomes. These contributions aim to advance the field of AI while making valuable information accessible to the broader community. Additionally, we provide open-source tools and datasets to support further research and development in both AI and video game development.
Focus
The AIIC is dedicated to developing AI solutions that tackle global challenges in healthcare, business, and engineering. While driving innovation on a broad scale, we also prioritize the digital advancement of the Kurdish language, ensuring it thrives in the modern technological landscape. Additionally, we explore the dynamic field of video game development, creating immersive experiences that engage and inspire players worldwide.
Research Fellows
Publications
# | Title | Cover |
Projects
Ratslayer
Ratslayer is a Vampire Survivors-inspired game where you battle waves of enemies as a quirky hero in a cartoony world, featuring unique power-ups and fast-paced action.
Zingil
Zingil is a language-based puzzle game that challenges players to solve linguistic riddles in an immersive world.
kurdishRoBERTa-language-detector-1B
This is a fine-tuned version of abdulhade/RoBERTa-large-SizeCorpus_1B, designed for detecting and classifying Kurdish and English text. Leveraging a custom bilingual corpus, this model is effective in distinguishing between these languages and accurately identifying text segments.
Kurdish-English Machine Translation with Transformers
This repository focuses on fine-tuning a Kurdish-English machine translation model using Hugging Face’s transformers library with MarianMT. The model is trained on a custom parallel corpus with a detailed pipeline that includes data preprocessing, bidirectional training, evaluation, and inference.
Kurdish Language Detector Model
This is a fine-tuned version of abdulhade/RoBERTa-large-SizeCorpus_1B, designed for detecting and classifying Kurdish and English text. Leveraging a custom bilingual corpus, this model is effective in distinguishing between these languages and accurately identifying text segments.
NER-FineTuing-RoBERTa
The project focuses on fine-tuning a pre-trained RoBERTa (Robustly Optimized BERT Pretraining Approach) model for Named Entity Recognition (NER) tasks. NER is a fundamental Natural Language Processing (NLP) task that involves identifying and classifying entities in text, such as names of people, organizations, locations, dates, and more.
Datasets
NER
This dataset is designed for NLP tasks like sequence tagging and NER. It includes 1,472 sentences, 9,528 tokens, and 42 unique tags, making it ideal for training and evaluating NER models and token classification.
Kurdish large text corpus
کۆڕپسێکی کۆکراوەی دەقی کوردی ناوەڕاست(سۆرانیە) کە قەبارەکەی پێکدێت لە ٤٣٠ میگا بایت
Number of rows: 773,800
Join AIIC in Shaping the Future!
- Explore collaboration opportunities
- Partner with us on groundbreaking AI projects
Contact Details:
- Email: [email protected]
- Location: 30m Avenue, University of Kurdistan Hewlêr, Opposite of the Main Reception Area