A5081117842- Natural Language Processing Techniques
- Text and Document Classification Technologies
- Topic Modeling
- Sentiment Analysis and Opinion Mining
- Spam and Phishing Detection
- Mathematics, Computing, and Information Processing
- Machine Learning and Data Classification
- Advanced Text Analysis Techniques
- Data Mining Algorithms and Applications
- Second Language Learning and Teaching
- Algorithms and Data Compression
- Multimodal Machine Learning Applications
- Engineering Education and Technology
- Rough Sets and Fuzzy Logic
- Educational Innovations and Challenges
- Multilingual Education and Policy
- Data Stream Mining Techniques
- Cloud Computing and Resource Management
- Online Learning and Analytics
- Intelligent Tutoring Systems and Adaptive Learning
University of New York Tirana
2018-2022
This paper analyses 15 AI policies for higher education from eight European countries, drawn individual universities, consortia of universities and government agencies. Based on an overview current research findings, it focuses the comparison different aspects among selected policies. The analysis distinguishes between four potential target groups, namely students, teachers, managers policy makers. aims at contributing to further development improvement through identification commonalities...
Named Entity Recognition (NER) deals with identifying personal, geographical, organizational or other entity types in a raw text. In this paper we propose the first NER model for Albanian language. Our is based on maximum entropy approach. We manually annotate corpus historical and political domains train models to generate classifiers that are able recognize relevant entities achieve good performance precision recall selected domains, despite scarcity of corpora fact marks research...
Neural Machine Translation (NMT) has seen a tremendous spurt of growth in less than ten years, and already entered mature phase. While considered as the most widely used solution for Translation, its performance on low-resource language pairs still remains sub-optimal compared to high-resource counterparts, due unavailability large parallel corpora. Therefore, implementation NMT techniques been receiving spotlight recent research arena, thus leading substantial amount reported this topic....
The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal value generative AI tools communities. However, development functional LLMs (\ie, multilingual LLMs) is bottlenecked by lack high-quality evaluation resources other than English. Moreover, current practices benchmark construction often translate English resources, ignoring regional cultural knowledge environments...