BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Natural Language Generation in the Wild - Daniel Beck\, University
  of Melbourne
DTSTART:20190705T110000Z
DTEND:20190705T120000Z
UID:TALK124930@talks.cam.ac.uk
CONTACT:Andrew Caines
DESCRIPTION:Traditional research in NLG focuses on building better models 
 and assessing their performance using clean\, preprocessed and curated dat
 asets\, as well as standard automatic evaluation metrics. From a scientifi
 c point-of-view\, this provides a controlled environment where different m
 odels can be compared and robust conclusions can be made. However\, these 
 controlled settings can drastically deviate from scenarios that happen whe
 n deploying systems in the real world. In this talk\, I will focus on what
  happens _before_ data is fed into NLG systems and what happens _after_ we
  generate outputs. For the first part\, I will focus on addressing heterog
 eneous data sources using tools from graph theory and deep learning. In th
 e second part\, I will talk about how to improve decision making from gene
 rated texts through Bayesian techniques\, using Machine Translation post-e
 diting as a test case.\n\n*Bio*:\nDaniel is a Lecturer at The University o
 f Melbourne. His main research topic is Natural Language Generation\, with
  a focus on Machine Translation. He is particularly interested in using to
 ols from Machine Learning\, Theoretical Computer Science and Statistics to
  address challenges in NLG that go beyond the usual input-output pipeline.
  He obtained a PhD from The University of Sheffield\, United Kingdom\, and
  his thesis on using Gaussian Processes for NLP applications received a Be
 st Thesis Award from the European Association for Machine Translation. Dan
 iel is also an advocate for queer and LGBT+ visibility in STEM\, in partic
 ular within NLP and Machine Learning. He is currently a board member of th
 e Widening NLP initiative (www.winlp.org)\, which foster inclusivity from 
 underrepresented groups in NLP. His personal webpage can be found at https
 ://beckdaniel.wordpress.com and he tweets at https://twitter.com/beck_dani
 el
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR