BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/675
DTSTAMP:20230914T125934Z
SUMMARY:Reordering Rules for Machine Translation Using Least General Genera
 lizations
DESCRIPTION:Speaker: Anamay Tengse\n\nAbstract: \nMachine translation has b
 een one of the key problems in computational linguistics. An important par
 t of the same is to get the order of words in the translated sentence corr
 ect. Numerous approaches exist that range from treating sentences as plain
  strings to those relying on sentence structure. Among the latter\, manual
 ly written rules as well as rules learnt by machine have been known to ben
 efit the intended purpose.\n\nIn this talk\, we discuss our work that lear
 ns rules for ordering words in the translated sentence using structural in
 formation about the original sentence. We view the problem as that of lear
 ning a declarative set of instructions and thereby deploy a technique used
  in program synthesis that uses an operator called LGG (Least General Gene
 ralization) (this work was done jointly with Ganesh Ramakrishnan and Amita
 bha Sanyal at IIT\, Bombay).\n \n
URL:https://www.tcs.tifr.res.in/web/events/675
DTSTART;TZID=Asia/Kolkata:20160422T153000
DTEND;TZID=Asia/Kolkata:20160422T170000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR