BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260408T174602Z
UID:Seminar-WiT-932@lxserverA.csc.liv.ac.uk.csc.liv.ac.uk
ORGANIZER:CN=Othon Michail:MAILTO:Othon.Michail@liverpool.ac.uk
DTSTART:20191002T130000
DTEND:20191002T140000
SUMMARY:Women in Technology Series
DESCRIPTION:Dr Danushka Bollegala: Gender-preserving Debiasing for Pre-trained Word Embeddings \n\nWord embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings. Taking gender-bias as a working example, we propose a debiasing method that preserves non-discriminative gender-related information, while removing stereotypical discriminative gender biases from pre-trained word embeddings. \n\n\n\nFollowing the talk, the audience will have the opportunity to direct questions to the speaker and also to members of the discussion panel.\n\nThe confirmed panel members are as follows:\n\n·         Prof. Simon Maskell (Electrical Engineering and Electronics)\n\n·         Dr. Rebecca Davnall (Philosophy)\n\n·         Dr. Zainab Hussain (Health Sciences), Chair of BAME Staff Network\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=932
LOCATION:Ashton Lecture Theatre
END:VEVENT
END:VCALENDAR