BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Natural Language Interpretation in Dialogue Systems - Dr Svetlana 
 Stoyanchev\, Speech Technology Group\, Toshiba CRL
DTSTART:20210309T120000Z
DTEND:20210309T130000Z
UID:TALK156769@talks.cam.ac.uk
CONTACT:Dr Kate Knill
DESCRIPTION:*Abstract*: Task-oriented dialogue systems are natural languag
 e interfaces that help the user to achieve a task\, such as finding inform
 ation from a data source\, making a food order\, or solving a problem.  Na
 tural language\, a universal communication interface\, is the input to a d
 ialogue system. The flexibility of natural language\, which allows ambigui
 ty and multiple correct ways to represent the same information\, presents 
 an interpretation challenge to such systems. In a referring expression\, a
  user may identify a previously discussed entity by specifying its propert
 ies\, e.g. `the Italian place’ or `the restaurant in the centre’.  An 
 intelligent system should correctly handle a user’s references to the pr
 eviously mentioned entities. \n\nIn this talk\, I will first give an overv
 iew of the approaches used to design a dialogue manager that relies on nat
 ural language understanding for interpreting user input.  Next\, I will de
 scribe the novel action state update approach (ASU) for utterance interpre
 tation. Using knowledge of the domain\, ASU interprets a user utterance wi
 thout a domain-specific natural language understanding component. We train
  the interpretation model using active learning on simulated dialogues in 
 the restaurant search domain. With both user-simulated and interactive hum
 an evaluations\, we show that the ASU approach successfully interprets use
 r utterances in a dialogue system\, including those with referring express
 ions.\n\n*Bio:* Dr. Svetlana Stoyanchev is a Research Engineer at  the Spe
 ech Technology Group in Cambridge Research Lab\, Toshiba Europe. She recei
 ved her Ph.D. in Computer Science from Stony Brook University. She held re
 search positions at The Open University\, Columbia University\,  AT&T Labs
  Research\, and Interactions Corporation. She served as a member of  IEEE 
 Speech and Language Processing Technical Committee and the program committ
 ees for research conferences and workshops\, including SIGDial\, ACL\, AAA
 I\, COLING\, and Interspeech. Her research interests include conversationa
 l and multimodal interfaces\, natural language understanding and generatio
 n\, argumentation in dialogue\, and error recovery in human-computer commu
 nication.\n
LOCATION:Zoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT
 2tDUT09
END:VEVENT
END:VCALENDAR
