no code implementations • 21 Apr 2023 • Laurent Lam, Pirashanth Ratnamogan, Joël Tang, William Vanhuffel, Fabien Caspani
Our research showed that when dealing with clean and relatively short entities, it is still best to use token classification-based approach, while the QA approach could be a good alternative for noisy environment or long entities use-cases.
no code implementations • 17 Nov 2022 • Joël Tang, Marina Fomicheva, Lucia Specia
We present a case study focusing on model understanding and regularisation to reduce hallucinations in NMT.