SereTOD: Call for Papers and Challenge Participation (EMNLP 2022 Workshop) - Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems

O
ozj@tsinghua.edu.cn
Thu, May 26, 2022 1:55 PM

SereTOD: Call for Papers and Challenge Participation

Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems

Co-located with EMNLP 2022

December 7, 2022 


Workshop website: http://seretod.org/

Paper submission: https://softconf.com/emnlp2022/seretod/

Challenge website: http://seretod.org/Challenge.html

Registration deadline for the Challenge is extended to July 1, 2022. 


Overview

Building task-oriented dialog (TOD) systems remains a label-intensive, time-consuming task for the reliance on manually labeled dialog data and annotated task-related knowledge base. However, unlabeled data are often easily available in many forms such as human-to-human dialogs, open-domain text corpus, and unstructured knowledge documents. Moreover, the nature of sequential decision making is not fully considered in current TOD systems.

The purpose of this workshop is to invite researchers from both academia and industry to share their perspectives on building semi-supervised and reinforced TOD systems, discuss challenges and advance the field in joint effort. A shared task and challenge will be organized for benchmarking and stimulating relevant researches, with a newly released large-scale, multi-domain TOD dataset which consists of 100K real-world dialogs. The Challenge consists of two tracks:

  • Information extraction from dialog transcripts (Track 1)

  • Task-oriented dialog systems (Track 2)

Topics of interest

We welcome submissions from all levels of methodologies, algorithms, models, system developments, applications and datasets towards semi-supervised and reinforced TOD systems. All types of semi-supervised techniques are welcome, such as, to name a few, pre-training, self-training, self-supervised, weakly-supervised, transfer learning for zero-shot or few-shots, latent-variable modeling, and domain adaptation, and data augmentation. Both online and offline reinforcement learning techniques are welcome. Topics of interest include, but are not limited to, the following:

  • General topics for task-oriented dialog systems

  • Semi-supervised information extraction and knowledge modeling

  • Grounded dialog with unstructured knowledge sources

  • Semi-supervised task-oriented dialog systems

  • Reinforced task-oriented dialog systems

  • User simulators

Awards for the Challenge

For each track, top three participant teams will be recognized with prizes RMB20,000, RMB15,000 and RBM10,000, respectively.

 

Important Dates

June 1, 2022: Training data release

July 1, 2022: Registration deadline for challenge (extended)

July 15, 2022: ACL Rolling Review paper due (submit via ARR)

August 14, 2022: Evaluation data release

August 21, 2022: Entry submission deadline

August 31, 2022: Evaluation results announced

September 7, 2022: Regular paper due (submit via softconf)

October 9, 2022: Notification of paper acceptance

October 16, 2022: Camera-ready papers due

December 7, 2022: EMNLP 2022 Workshop Date

 

Submissions

  • Regular Submissions

We accept long papers (8 pages plus unlimited references), short papers (4 pages plus unlimited references), and system description papers for the challenge (in either long or short formats), which should conform to ACL submission information.

  • Non-Archival Submissions

Authors can submit a paper up to 2-8 pages long, with unlimited reference and supplementary material pages. The accepted papers can opt to be non-archival, i.e., the work could be published elsewhere before or after the workshop.

  •  Review Process

All submissions will be peer-reviewed by at least two reviewers. The reviewing process will be double-blinded at the level of the reviewers. Authors are responsible for anonymizing the submissions.

  •  Submission Links and Deadlines

SereTOD Workshop will accept regular submissions through the softconf system, as well as commitment of already reviewed papers through the ACL Rolling Review (ARR) system.

July 15, 2022: ARR paper due (submit via ARR)
September 7, 2022: Regular paper due (submit via softconf)

Organizers

Zhijian Ou, Tsinghua University

Junlan Feng, China Mobile

Juanzi Li, Tsinghua University

For any questions, please feel free to contact: seretod2022 (at) gmail (dot) com

 

Looking forward to your participation!

SereTOD: Call for Papers and Challenge Participation Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems Co-located with EMNLP 2022 December 7, 2022  --- Workshop website: <http://seretod.org/> Paper submission: <https://softconf.com/emnlp2022/seretod/> Challenge website: <http://seretod.org/Challenge.html> **Registration deadline for the Challenge is extended to July 1, 2022.**  --- **Overview** Building task-oriented dialog (TOD) systems remains a label-intensive, time-consuming task for the reliance on manually labeled dialog data and annotated task-related knowledge base. However, unlabeled data are often easily available in many forms such as human-to-human dialogs, open-domain text corpus, and unstructured knowledge documents. Moreover, the nature of sequential decision making is not fully considered in current TOD systems. The purpose of this workshop is to invite researchers from both academia and industry to share their perspectives on building semi-supervised and reinforced TOD systems, discuss challenges and advance the field in joint effort. A shared task and challenge will be organized for benchmarking and stimulating relevant researches, with a newly released large-scale, multi-domain TOD dataset which consists of **100K real-world dialogs**. The Challenge consists of two tracks: * Information extraction from dialog transcripts (Track 1) * Task-oriented dialog systems (Track 2) **Topics of interest** We welcome submissions from all levels of methodologies, algorithms, models, system developments, applications and datasets towards semi-supervised and reinforced TOD systems. All types of semi-supervised techniques are welcome, such as, to name a few, pre-training, self-training, self-supervised, weakly-supervised, transfer learning for zero-shot or few-shots, latent-variable modeling, and domain adaptation, and data augmentation. Both online and offline reinforcement learning techniques are welcome. Topics of interest include, but are not limited to, the following: * General topics for task-oriented dialog systems * Semi-supervised information extraction and knowledge modeling * Grounded dialog with unstructured knowledge sources * Semi-supervised task-oriented dialog systems * Reinforced task-oriented dialog systems * User simulators **Awards for the Challenge** For each track, top three participant teams will be recognized with prizes RMB20,000, RMB15,000 and RBM10,000, respectively.   **Important Dates** June 1, 2022: Training data release July 1, 2022: Registration deadline for challenge (extended) July 15, 2022: ACL Rolling Review paper due (submit via [ARR](https://aclrollingreview.org/)) August 14, 2022: Evaluation data release August 21, 2022: Entry submission deadline August 31, 2022: Evaluation results announced September 7, 2022: Regular paper due (submit via [softconf](https://softconf.com/emnlp2022/seretod/)) October 9, 2022: Notification of paper acceptance October 16, 2022: Camera-ready papers due December 7, 2022: EMNLP 2022 Workshop Date   **Submissions** * Regular Submissions We accept long papers (8 pages plus unlimited references), short papers (4 pages plus unlimited references), and system description papers for the challenge (in either long or short formats), which should conform to ACL submission information. * Non-Archival Submissions Authors can submit a paper up to 2-8 pages long, with unlimited reference and supplementary material pages. The accepted papers can opt to be non-archival, i.e., the work could be published elsewhere before or after the workshop. *  Review Process All submissions will be peer-reviewed by at least two reviewers. The reviewing process will be double-blinded at the level of the reviewers. Authors are responsible for anonymizing the submissions. *  Submission Links and Deadlines SereTOD Workshop will accept regular submissions through the softconf system, as well as commitment of already reviewed papers through the ACL Rolling Review (ARR) system. **July 15, 2022**: ARR paper due (submit via [ARR](https://aclrollingreview.org/))\ **September 7, 2022**: Regular paper due (submit via [softconf](https://softconf.com/emnlp2022/seretod/)) **Organizers** Zhijian Ou, Tsinghua University Junlan Feng, China Mobile Juanzi Li, Tsinghua University For any questions, please feel free to contact: seretod2022 (at) gmail (dot) com   Looking forward to your participation!