Martino Mensio

Papers

Total Citations

H-Index

About

Martino Mensio is a researcher at the intersection of artificial intelligence and robotics, with a primary focus on making deep learning systems more transparent, robust, and fair. His work centers on mitigating bias in neural networks by integrating structured knowledge bases, particularly in the domain of natural language understanding for robotic systems. In his most cited paper, "Mitigating bias in deep nets with knowledge bases: The case of natural language understanding for robots" (2020), Mensio demonstrates how incorporating FrameNet—a rich semantic knowledge base—can guide an LSTM-based semantic parser to learn correct linguistic representations, thereby reducing the harmful biases that often arise from purely data-driven approaches. This contribution is especially critical for real-world applications where robots must interpret human commands accurately and equitably. Though early in his career, Mensio’s work has already garnered attention (2 citations), signaling its relevance to the growing field of trustworthy AI. His research offers a promising path toward more interpretable and ethically aligned AI systems, making him a notable voice in the push for responsible machine learning.