ISCA - International Speech
Communication Association

ISCApad Archive  »  2015  »  ISCApad #206  »  Events  »  Other Events  »  (2015-xx-xx) Dialog State Tracking Challenge 4

ISCApad #206

Thursday, August 20, 2015 by Chris Wellekens

3-3-22 (2015-xx-xx) Dialog State Tracking Challenge 4


              Dialog State Tracking Challenge  4
                 First Call for Participation
                 April 1, 2015 (Registration opens)

*--- 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.


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


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


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)

Seokhwan Kim: kims AT
Luis Fernando D?Haro: luisdhe AT
1 Fusionopolis Way, #21-01, Singapore 138632
Fax: (+65) 6776 1378

*--- REFERENCES ---*

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