BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260409T120508Z
UID:Seminar-dept-410@lxserverA.csc.liv.ac.uk.csc.liv.ac.uk
ORGANIZER:CN=Lutz Oettershagen:MAILTO:Lutz.Oettershagen@liverpool.ac.uk
DTSTART:20160517T130000
DTEND:20160517T140000
SUMMARY:School Seminar Series
DESCRIPTION:Dr. Andreas Vlachos: Natural language understanding with imitation learning\n\nIn this talk I will focus on the machine learning approach used in most of my work in natural language understanding, namely imitation learning. In this paradigm, structured prediction is converted into a sequence of classification actions which are learnt by appropriate generation of cost-sensitive training examples, so that the impact of the actions is assessed globally while maintaining flexibility in feature extraction. Experiments in a variety of tasks in biomedical text mining, information extraction and semantic parsing demonstrate the broad applicability and the competitive performance of imitation learning. Finally, time permitting, I will give an overview of my recent work in fact-checking and language modelling.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=410
LOCATION:Ashton Lecture Theater
END:VEVENT
END:VCALENDAR