BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Detecting paraphrases using recursive autoencoders - Feynman Liang
DTSTART:20151105T143000Z
DTEND:20151105T160000Z
UID:TALK62311@talks.cam.ac.uk
CONTACT:Yingzhen Li
DESCRIPTION:In this RCC we will talk about work from Richard Socher applyi
 ng deep learning to paraphrase detection (i.e. determining when two senten
 ces carry the same meaning). We will give an introduction to distributiona
 l semantics and models/techniques relevant to the sentence similarity task
 \, then dive deep on the novel contributions of the referenced paper and c
 ompare it against existing work. We will conclude with surveying the curre
 nt state of the art and highlighting potential directions for additional r
 esearch.\n\n*optional reading*\nPaper and Code: \n"Dynamic Pooling And Unf
 olding Recursive Autoencoders For Paraphrase Detection":http://www.socher.
 org/index.php/Main/DynamicPoolingAndUnfoldingRecursiveAutoencodersForParap
 hraseDetection
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR