Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Latent Variable Models in Dialogue Generation
Speaker:Xiaoyu Shen
coming from:Fachrichtung Informatik - Saarbrücken
Speakers Bio:Graduate Student Informatics, UdS
Event Type:PhD Application Talk
Visibility:D1, D2, D3, D4, D5, SWS, RG1, MMCI
We use this to send out email in the morning.
Level:Public Audience
Language:English
Date, Time and Location
Date:Tuesday, 10 October 2017
Time:09:30
Duration:60 Minutes
Location:Saarbrücken
Building:E1 4
Room:R024
Abstract
Open-domain dialogue generation is an important research area and is drawing more and more attention in the past years. Nowadays, the vast amount of conversational corpora and the popularity of seq2seq models have made it possible to design data-driven, end-to-end trainable dialogue systems without verbose handcrafted rules. However, vanilla seq2seq models stochastical variations only at the token level, seducing the system to gain immediate short rewards and neglect the long-term structure. One way of attenuating this problem is by introducing “latent variables”, which stand for high-level sentence representations to help guide the generating process. This talk explains the application of latent variable models on dialogue generation and two main challenges: uninterpretability of latent variables and difficulty of training. We propose some solving strategies to these challenges respectively and validate the effectiveness.
Contact
Name(s):IMPRS Office Team
Phone:0681 93251800
EMail:--email address not disclosed on the web
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):
Created by:Stephanie Jörg/MPI-INF, 10/09/2017 01:21 PMLast modified by:Uwe Brahm/MPII/DE, 10/10/2017 07:01 AM
  • Stephanie Jörg, 10/09/2017 01:29 PM -- Created document.