BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Gender Bias in Machine Translation Systems - Stefanie Ullmann (she
 /her)\, CRASSH
DTSTART:20231017T121000Z
DTEND:20231017T130000Z
UID:TALK203911@talks.cam.ac.uk
CONTACT:109562
DESCRIPTION:You may have read headlines such as “Google Translate is sex
 ist” in the past. While machine translation software has become a freque
 ntly used tool for many of us and can\, indeed\, be very useful to master 
 communication in multilingual settings\, these systems also have the prope
 nsity to carry inherent risks and imbalances. \nIn this talk\, I will look
  at encoded biases in automated translation between languages with differe
 nt grammatical genders (specifically English and German). I will address t
 he following questions:\nWhat is grammatical gender and why can it pose di
 fficulties in translation?\nHow does gender bias manifest in machine trans
 lation? \nWhat can be done to mitigate this form of bias?\nI will present 
 the results of a corpus analysis of representative training data and\, fin
 ally\, discuss different algorithmic approaches to addressing the problem.
 \n\nAbout the speaker:\nDr Stefanie Ullmann is a Research Associate at the
  Centre for Research in the Arts\, Social Sciences and Humanities as well 
 as Darwin College. She is a linguist and her research focuses on the use o
 f language in socio-political settings and the social implications of comm
 unications technologies.
LOCATION:Richard King room\, Darwin College
END:VEVENT
END:VCALENDAR