The IJCNLP-AACL 2023 System Demonstration Program Committee invites proposals for the Demonstrations Program. Submissions may range from early research prototypes to mature production-ready systems. Of particular interest are publicly available open-source or open-access systems. We strongly encourage demonstrations of industrial systems that are technologically innovative, given the current state of the art of theory and applied research in computational linguistics.
Areas of interest include all topics related to theoretical and applied computational linguistics, such as (but not limited to) the topics listed on the main conference website. Submitted systems may be of the following types:
- Natural Language Processing systems or system components
- Application systems using language technology components
- Software tools for computational linguistics research
- Software for demonstration or evaluation
- Software supporting learning or education
- Tools for data visualization and annotation
- Development tools
Accepted submissions will be published in a companion volume of the IJCNLP-AACL 2023 conference proceedings, and will be presented during a demo session with an accompanying poster.
Please note: Commercial sales and marketing activities are NOT appropriate in the Demonstration Program and should be arranged as part of the Exhibit Program.
|Submission deadline:||July 7, 2023|
|Notification of acceptance:||September 7, 2023|
|Camera-ready submission:||September 15, 2023|
IJCNLP-AACL2023 accepts proposals for system demonstrations from Softconf START https://softconf.com/ijcnlp2023/demo/.
Developers should outline the design of their system and provide sufficient details to allow the evaluation of its validity, quality, and relevance to computational linguistics. Discussion of limitations, use cases as well as related systems should also be included. If the demo has the potential for ethical concerns (for instance, displaying medical patient data), details should be given as to how the ethical issues are resolved in the demo (for instance, only anonymized records are used).
Pointers to web sites running a demo preview will also be helpful. For non-web-based demos, it is possible to submit a short (~2 minute) screencast video demonstrating the system. This screencast will be used to evaluate the paper, but won’t be published unless requested. We encourage the authors to include visual aids (e.g., screenshots, snapshots, or diagrams) in the paper. However, there will be a place on the START website to upload additional material, if needed. If you choose to submit a screencast, please upload the video to some hosting site (YouTube, Vimeo, etc.) and include the link in your submission.
Demo submissions should also clearly indicate if any computer equipment is expected to be provided by the local organizer. If so, please specify desired hardware platform, hard disk and memory capacity, operating system and other software needed in order to run the demo.
Style files should meet the requirements of the IJCNLP-AACL main conference. Submissions may consist of up to 6 pages (excluding references). Submissions must conform to the IJCNLP-AACL 2023 official style guidelines and they must be in PDF format. The submissions have to be original work (unpublished), as the publication in IJCNLP-AACL will be archival. Following ACL 2023, authors may include a “Limitations” section in their demo submission (not mandatory). The “Limitations” statement can be placed after the conclusion but before the references and will not count toward the page limit.
Reviewing will be single-blind, so authors do not need to conceal their identity. The paper should include the authors’ names and affiliations. Self-references are also allowed. Papers with unresolved ethical issues will not be accepted.
Best Demo Award
IJCNLP-AACL 2023 will have a Best Demo Award, honoring a system demonstration that brings together conceptual innovation and practical usability, and encouraging researchers to make their code publicly available in the form of an effective, easy-to-use, runnable system.
- Sriparna Saha, Indian Institute of Technology Patna, India
- Herry Sujaini, University of Tanjungpura, Indonesia