ISCA - International Speech
Communication Association


ISCApad Archive  »  2015  »  ISCApad #207  »  Events  »  Other Events  »  (2015-xx-xx) Dialog State Tracking Challenge 4

ISCApad #207

Friday, September 25, 2015 by Chris Wellekens

3-3-8 (2015-xx-xx) Dialog State Tracking Challenge 4
  

 

*****************************************************************
              Dialog State Tracking Challenge  4
                 First Call for Participation
                 April 1, 2015 (Registration opens)
      http://www.colips.org/workshop/dstc4/index.html
******************************************************************

*--- MOTIVATION ---*

Dialog state tracking is one of the key sub-tasks of dialog management, which defines the representation of dialog states and updates them at each moment on a given on-going conversation. To provide a common benchmark for this task, the first Dialog State Tracking Challenge (DSTC) was organized [1]. More recently, Dialog State Tracking Challenges 2 & 3 have been successfully completed [2].

In this fourth edition of the Dialog State Tracking Challenge, we will focus on a dialog state tracking task on human-human dialogs. We expect these shared efforts on human dialogs will contribute to progress in developing much more human-like systems. In addition to the main task, we propose four pilot tracks for the core components in developing end-to-end dialog systems, and an open track based on the same dataset.

The provided dataset consists of 35 dialog sessions between 3 tour guides and 35 tourists with a total length of 21 hours, plus their manual transcriptions and speech act and semantic labels annotations at turn level.


*--- PROPOSED TASKS ---*

Main task:
     ? Dialog State Tracking at Sub-dialog Level: Fill out the frame of slot-value pairs for the current sub-dialog considering all dialog history prior to the turn. A baseline system will be provided.

Pilot tasks (optional):
     ? Spoken language understanding: Tag a given utterance with speech acts and semantic slots.
     ? Speech act prediction: Predict the speech act of the next turn imitating the policy of one speaker.
     ? Spoken language generation: Generate a response utterance for one of the participants.
     ? End-to-end system: Develop an end-to-end system playing the part of a guide or a tourist.

Open track (optional):
?    Proposed by teams willing to work on any task of their interest over the provided dataset


*--- IMPORTANT DATES ---*

01 Apr 2015: Registration opens
15 Apr 2015: Labeled training data is released
17 Aug 2015: Unlabeled test data is released
31 Aug 2015: Entry submission deadline
04 Sep 2015: Evaluation results are released
      Jan 2016: Results presented at IWSDS 2016

  
*--- ORGANIZING COMMITTEE ---*

Seokhwan Kim (I2R, Singapore)
Luis Fernando D?Haro (I2R, Singapore)
Rafael E. Banchs (I2R, Singapore)
Jason D. Williams (Microsoft, USA)
Matthew Henderson (U. Cambridge, UK)


*--- CONTACT DETAILS ---*
Seokhwan Kim: kims AT i2r.a-star.edu.sg
Luis Fernando D?Haro: luisdhe AT i2r.a-star.edu.sg
1 Fusionopolis Way, #21-01, Singapore 138632
Fax: (+65) 6776 1378


*--- REFERENCES ---*
[1] http://research.microsoft.com/en-us/events/dstc/
[2] http://camdial.org/~mh521/dstc/




Back  Top


 Organisation  Events   Membership   Help 
 > Board  > Interspeech  > Join - renew  > Sitemap
 > Legal documents  > Workshops  > Membership directory  > Contact
 > Logos      > FAQ
       > Privacy policy

© Copyright 2024 - ISCA International Speech Communication Association - All right reserved.

Powered by ISCA