Simone Conia
Assistant Professor
Sapienza University of Rome
Assistant Professor
Sapienza University of Rome
I am an Assistant Professor at Sapienza University of Rome, where I conduct research at the intersection of Natural Language Processing and Machine Learning. My work focuses on advancing the capabilities and understanding of Large Language Models, particularly in multilingual settings.
Author of over 40 publications in top-tier conferences (including ACL, EMNLP, AAAI, IJCAI, NAACL), I have contributed significantly to the field of AI and NLP. My research has been recognized with multiple awards, including the Outstanding Paper Award at EMNLP 2024 and NAACL 2021. Earlier in my career, I was also a Distinguished PC at IJCAI, Honor Student at Sapienza, a CyberChallenge.IT podium winner, and winner of the Google Startup Workshop.
Understanding and improving the capabilities of modern language models
Developing NLP systems that work across diverse languages
Enhancing language models with external knowledge retrieval
Creating robust metrics and benchmarks for NLP systems
Research collaborations and projects
Investigating the fundamental capabilities and limitations of large language models, with a focus on improving their reasoning abilities and reducing hallucinations.
Developing robust natural language processing systems that can effectively handle multiple languages, with particular attention to low-resource languages.
Enhancing language models by integrating external knowledge retrieval mechanisms to improve factual accuracy and reduce knowledge gaps.
Simone Conia, Daniel Lee, Min Li, Umar Farooq Minhas, Saloni Potdar, Yunyao Li
In Proceedings of EMNLP 2024
KG-MT introduces a novel end-to-end approach that integrates multilingual knowledge graphs into neural machine translation via dense retrieval, enabling significant improvements in translating culturally-nuanced entity names compared to state-of-the-art systems.
Simone Conia, Min Li, Daniel Lee, Umar Minhas, Ihab Ilyas, Yunyao Li
In Proceedings of EMNLP 2023
M-NTA is a novel unsupervised approach that combines Machine Translation, Web Search, and Large Language Models to automatically generate high-quality multilingual textual information for knowledge graphs, significantly improving coverage and precision for non-English languages.
Simone Conia, Andrea Bacciu, Roberto Navigli
In Proceedings of NAACL 2021
This paper introduces a unified model for cross-lingual Semantic Role Labeling that learns to map heterogeneous linguistic formalisms across languages without word alignment or translation, enabling robust and simultaneous annotation with multiple inventories.
Sapienza University of Rome
Leading research in Natural Language Processing with focus on Large Language Models, Multilingual NLP, and Retrieval Augmented Generation. Teaching graduate courses in Computer Science.
Apple
Collaborating on research projects related to natural language understanding and generation, focusing on improving the performance of language models in real-world applications, especially in multilingual contexts.
Apple
Conducted research on multilingual language models, focusing on enhancing their understanding and generation capabilities across various languages. Developed novel methodologies for improving knowledge-related question answering tasks across multiple languages.
Sapienza University of Rome
Specialized in Natural Language Processing and Machine Learning. Dissertation on multilingual language understanding and generation.
I'm always interested in discussing research collaborations and innovative projects in NLP and AI.