BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260921T002044Z
UID:Seminar-dept-1033@lxserverM.csc.liv.ac.uk
ORGANIZER:CN=Lutz Oettershagen:MAILTO:Lutz.Oettershagen@liverpool.ac.uk
DTSTART:20230223T150000
DTEND:20230223T160000
SUMMARY:School Seminar Series
DESCRIPTION:Dr. Nikolaos Aletras: Towards compute efficient large language models\n\nLarge language models (LLMs) are really effective when adapted in various downstream NLP tasks. However, pre-training requires access to large compute resources. In this talk, I will present our work on (1) speeding up pre-training with simple objectives compared to the widely used masked language modelling, (2) how the choice of pre-training objective affects LLMs capturing linguistic information, and (3) how we can support an unlimited vocabulary with a relatively small number of parameters.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=1033
LOCATION:Ashton Lecture Theatre
END:VEVENT
END:VCALENDAR