The purpose of this workshop is to invite researchers from both academia and industries to bring their perspectives on building semi-supervised and reinforced task-oriented dialog (TOD) systems and to advance the field in joint effort.
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
We accept long papers (8 pages plus unlimited references and appendix, on submission), short papers (4 pages plus unlimited references and appendix, on submission), and system description papers for the challenge (in either long or short formats), which should conform to ACL submission information. Final versions of long papers will be given one additional page of content (up to 9 pages) so that reviewers' comments can be taken into account, and for short paper, up to 5 pages.
Regular Submissions (whether long or short) will be complied into: Proceedings of the 2022 Workshop on Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems (SereTOD), which will be published in the ACL Anthology.
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.
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.
All long and short submissions must follow the two-column ACL format, which are available as an Overleaf template and also downloadable directly (Latex and Word). Submissions must conform to the official ACL style guidelines, which are contained in these templates. Submissions must be electronic, in PDF format.
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 17, 2022: Regular paper due (submit via softconf)
October 2, 2022: ARR commitment due (commit via OpenReview)
October 7, 2022: Submission of EMNLP manuscripts with reviews (submit via softconf)
Please refer to the ARR Call for Papers for detailed information about submission guidelines to ARR. The commitment deadline for SereTOD 2022 (deadline for authors to submit their reviewed papers, reviews, and meta-review to SereTOD 2022) is October 2, 2022. Note that the paper needs to be fully reviewed by ARR in order to make a commitment, thus the latest date for ARR submission will be July 15, 2022.
Manuscripts that have been reviewed for EMNLP 2022 and were rejected have the opportunity to be considered for publication in the SereTOD Workshop proceedings. The deadline for submitting EMNLP manuscripts and reviews is October 7, 2022.
The manuscript, the review, and optionally with a response letter, should be contained in one PDF file and submitted via softconf.
The reviews will be verified with EMNLP 2022 for integrity check.