BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Mexico/General
BEGIN:DAYLIGHT
DTSTART:20210404T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20211031T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210811T013747Z
UID:286D4585-8C29-4A11-93DB-710D89063B20
DTSTART;TZID=Mexico/General:20210809T090000
DTEND;TZID=Mexico/General:20210809T100000
DESCRIPTION:Abstract\nPrevious work on task-oriented dialogue systems are u
 sually restricted to a limited coverage of APIs related to the set of task
 s considered in the application domain. However\, users oftentimes have do
 main related requests that are not covered by these APIs\, even for their 
 task-focused intents. To enable natural interactions with machines\, we pr
 opose to expand the coverage of task-oriented dialogue systems by incorpor
 ating external\, unstructured knowledge sources\, such as web documents re
 lated to the task domain. In this talk\, after a brief overview of dialogu
 e systems research\, I’ll present how we integrate knowledgeable respons
 es into task-oriented conversations\, and summarize our learnings from our
  work as well as public challenges we've been organizing in this area.\n\n
 Speaker(s): Dr. Dilek Hakkani-Tür\, \n\nGuadalajara\, Jalisco\, Mexico\, 
 Virtual: https://events.vtools.ieee.org/m/270839
LOCATION:Guadalajara\, Jalisco\, Mexico\, Virtual: https://events.vtools.ie
 ee.org/m/270839
ORGANIZER:r.calderonr@ieee.org
SEQUENCE:9
SUMMARY:Conversational Machines: Towards bridging the chasm between task-or
 iented and social conversations.
URL;VALUE=URI:https://events.vtools.ieee.org/m/270839
X-ALT-DESC:Description: <br /><div><strong>Abstract</strong></div>\n<div>Pr
 evious work on task-oriented dialogue systems are usually restricted to a 
 limited coverage of APIs related to the set of tasks considered in the app
 lication domain. However\, users oftentimes have domain related requests t
 hat are not covered by these APIs\, even for their task-focused intents. T
 o enable natural interactions with machines\, we propose to expand the cov
 erage of task-oriented dialogue systems by incorporating external\, unstru
 ctured knowledge sources\, such as web documents related to the task domai
 n. In this&nbsp\;talk\, after a brief overview of dialogue systems researc
 h\, I&rsquo\;ll present how we integrate knowledgeable responses into task
 -oriented conversations\, and summarize our learnings from our work as wel
 l as public challenges we've been organizing in this area.</div>
END:VEVENT
END:VCALENDAR