Papers by Moran Mizrahi

    2 papers
    Coming to Terms: Automatic Formation of Neologisms in Hebrew (2020.findings-emnlp)

    Copied to clipboard

    Challenge: a new algorithm to generate neologisms in spoken languages relies on human creativity . a system to automatically generate a dictionary of new words is proposed . we focus on the Hebrew language due to the unusual regularity of its noun formation .
    Approach: They propose a system to automatically suggest new words in the Hebrew language . they focus on the Hebrew because of the unusual regularity of its noun formation .
    Outcome: The proposed system generates high-quality outputs and enhances human creativity . it is compared to other systems and tested on the Hebrew language .
    🧑‍🍳 Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination (2026.tacl-1)

    Copied to clipboard

    Challenge: Large Language Models excel at many tasks, yet struggle to generate truly creative ideas.
    Approach: They propose a novel approach that enhances Large Language Models' creativity by manipulating structured representations of existing ideas.
    Outcome: The proposed model outperforms GPT-4o in novelty and diversity and outperformed GPT-0 in creative generation.

    What is GenGO?

    GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

    Information

    About
    Limitations