BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Interpretable Multi-hop Question Answering - Zhenyun Deng (Univers
 ity of Cambridge)
DTSTART:20230526T110000Z
DTEND:20230526T120000Z
UID:TALK200032@talks.cam.ac.uk
CONTACT:Michael Schlichtkrull
DESCRIPTION:Abstract:\n\nMulti-hop question answering (QA) requires reason
 ing over multiple documents to answer a complex question and provide expla
 nations for the answer. Most existing QA systems use an end-to-end model t
 o answer natural language questions\, making it difficult to demonstrate t
 hat a model has performed the desired reasoning to predict the correct ans
 wer. As a result\, most QA systems have fallen short of the goal of answer
 ing multi-hop questions in an interpretable fashion using an acceptable re
 asoning pattern. My research attempts to tackle two distinct problems in m
 ulti-hop QA: i) how to build an interpretable QA system to answer a comple
 x multi-hop question\; ii) how to learn knowledge for the new QA tasks whi
 le retaining the knowledge learned on previous QA tasks. The goal of this 
 research is to help humans better understand and trust the mechanism of a 
 QA system using multi-hop reasoning.\n\nBio:\n\nI'm Zhenyun Deng\, a postd
 octoral research associate working with Prof. Andreas Vlachos on automated
  fact checking at the Department of Computer Science and Technology at the
  University of Cambridge. Before that\, I received my PhD from the Univers
 ity of Auckland\, New Zealand. My PhD research focuses on interpretable mu
 lti-hop question answering\, which aims to reason over multiple documents 
 to answer a complex question and provide explanations for the \nanswer.
LOCATION:Computer Lab\, SS03
END:VEVENT
END:VCALENDAR