activity
20142024
most citedMultitask Kernel-based Learning with Logic Constraints

12 citations · 34 across the 16 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2025

From Arabic Text to Puzzles: LLM-Driven Development of Arabic Educational Crosswords

Kamyar Zeinalipour, Mohamed Zaky Saad, Marco Maggini +1

We present an Arabic crossword puzzle generator from a given text that utilizes advanced language models such as GPT-4-Turbo, GPT-3.5-Turbo and Llama3-8B-Instruct, specifically dev…

cs.CL2024

Harnessing LLMs for Educational Content-Driven Italian Crossword Generation

Kamyar Zeinalipour, Achille Fusco, Asya Zanollo +2

In this work, we unveil a novel tool for generating Italian crossword puzzles from text, utilizing advanced language models such as GPT-4o, Mistral-7B-Instruct-v0.3, and Llama3-8b-…

cs.CL20241 cited

Automating Turkish Educational Quiz Generation Using Large Language Models

Kamyar Zeinalipour, Yusuf Gökberk Keptiğ, Marco Maggini +1

Crafting quizzes from educational content is a pivotal activity that benefits both teachers and students by reinforcing learning and evaluating understanding. In this study, we int…

cs.CL2024

Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles

Andrea Zugarini, Kamyar Zeinalipour, Surya Sai Kadali +3

Crossword puzzles are popular linguistic games often used as tools to engage students in learning. Educational crosswords are characterized by less cryptic and more factual clues t…

cs.CL20242 cited

ArabIcros: AI-Powered Arabic Crossword Puzzle Generation for Educational Applications

Kamyar Zeinalipour, Mohamed Zaky Saad, Marco Maggini +1

This paper presents the first Arabic crossword puzzle generator driven by advanced AI technology. Leveraging cutting-edge large language models including GPT4, GPT3-Davinci, GPT3-C…