Open Knowledge Graphs Canonicalization using Variational Autoencoders
- Sarthak Dash
- Gaetano Rossiello
- et al.
- 2021
- EMNLP 2021
Gaetano Rossiello is a Research Scientist at the IBM Thomas J. Watson Research Center, specializing in Natural Language Processing (NLP), Knowledge Representation and Reasoning (KRR), and Machine Learning (ML). His research focuses on advancing the capabilities of AI agentic systems through innovations in large language models (LLMs), multi-modal retrieval-augmented generation (RAG), and automated tool routing.
Gaetano's work explores reasoning methodologies across the pre-training, fine-tuning, and inference stages of model development. He addresses key challenges in areas such as code generation, data management, information retrieval, question answering, and Text2SQL, with the goal of enhancing knowledge discovery and analytics within enterprise environments.
His research has been presented at leading artificial intelligence conferences, and he holds multiple U.S. patents. He has received several IBM awards, including an Outstanding Research Accomplishment for his contributions to the 'GTS TSS Multi-Vendor Services Transformation' and research accomplishment awards for his work on the 'Deep Thinking Question Answering' and 'AI Recommender' projects.
Gaetano earned his Ph.D. in Computer Science and Mathematics from the University of Bari 'Aldo Moro' in Italy. His doctoral dissertation, "Leveraging Distributional and Relational Semantics for Knowledge Extraction from Textual Corpora," was recognized by the Italian Association for Artificial Intelligence (AIxIA) as the best Ph.D. thesis in AI.