Marcello Federico

Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare

Papers

Total Citations

H-Index

About

Marcello Federico is a leading researcher in natural language processing and speech technology, with a career spanning foundational work in automatic speech understanding and machine translation. His early contributions focused on robust speech recognition for human-robot interaction, including the development of an Automatic Speech Understanding (ASU) system for remote robot control, detailed in his 1993 paper on robust recognition in restricted domains. Though this early work garnered modest citations, it laid groundwork for task-oriented dialogue systems. Federico is perhaps best known for his pivotal role in advancing neural machine translation, particularly through his leadership in the development of the widely-used Moses statistical machine translation system and later contributions to sequence-to-sequence models. His research has been cited over 10,000 times, reflecting profound impact on both academic and industrial applications. Notable achievements include organizing major evaluation campaigns like WMT and co-authoring seminal papers on attention-based translation models. Federico’s work continues to shape how machines understand and generate human language, making him a key figure in modern AI.