Call for System Demonstrations

The EMNLP 2021 System Demonstration Program Committee invites proposals for the Demonstrations Program. Demonstrations may range from early research prototypes to mature production-ready systems. Of particular interest are publicly available open-source or open-access systems. We additionally strongly encourage demonstrations of industrial systems that are technologically innovative given the current state of the art of theory and applied research in natural language processing. Each submitted demonstration must be accompanied by a submitted paper describing the system (see below).

Areas of interest include all topics related to theoretical and applied natural language processing, such as (but not limited to) the topics listed on the main conference website.

We especially welcome systems for model analysis and interpretation. Submitted systems may be of the following types:

  • Natural language processing systems or system components
  • Application systems using language technology components
  • Software tools for natural language processing research
  • Software for demonstration or evaluation
  • Software supporting learning or education
  • Tools for data visualization and annotation
  • Tools for model inspection
  • Development tools

Papers describing accepted demonstrations will be published in a companion volume of the EMNLP 2021 conference proceedings.
Please note: Commercial sales and marketing activities are not appropriate in the Demonstrations Program and should be arranged as part of the Exhibit Program.

Best Demo Award

As in previous years, EMNLP 2021’s demo track will feature a Best Demo Award. We hope to encourage researchers to make their code publicly available and in the form of an easy-to-use, runnable system.

Important Dates

  • Paper submission deadline: Thursday, July 1, 2021
  • Notification of acceptance: Wednesday, August 25, 2021
  • Camera-ready submission: Thursday, September 9, 2021

All deadlines are 11.59 pm UTC -12h ("anywhere on Earth").

Submission of papers describing demonstrations

A paper submitted to accompany a demonstration should outline the design of the system and provide sufficient details to allow the evaluation of its validity, quality, and relevance to natural language processing. A paper can do this by addressing the following questions:

  • What problem does the proposed system address?
  • Why is the system important and what is its impact?
  • What is the novelty in the approach/technology on which this system is based?
  • Who is the target audience?
  • How does the system work?
  • How does it compare with existing systems?
  • How is the system licensed?

Paper submission is electronic, using the Softconf START conference management system.

Style files should meet the requirements of the EMNLP main conference. Submissions may consist of up to 6 pages, plus unlimited references. Submissions must conform to the EMNLP 2021 official style guidelines and they must be in PDF format. The submissions have to be original work (unpublished), as the publication in EMNLP will be archival.

Multiple Submission Policy

We follow the Multiple Submission Policy of the CFP of the EMNLP 2021 main conference. The paper has to be written specifically for this conference and cannot be submitted elsewhere.

Reviewing Policy

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.

Demo Details

As the conference might be fully or partially virtual, all the demos might have to be presented online via a video conference tool. Therefore, we strongly recommend all demos are provided via one of the following formats: (1) A live demo website; or (2) A website with a downloadable installation package of the demo; unless this is impossible because some special hardware is required or access is otherwise limited. The exact details of the conference and demo session are still to be worked out and will be announced in due time.

You are encouraged to submit a short (~2 minute) screencast video demonstrating the system together with your paper submission. 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. Authors will also be able to upload and submit 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 paper submission. To ensure accessibility for deaf or hard-of-hearing viewers, we encourage authors to caption videos prior to submission.

Demo co-chairs:

  • Heike Adel (Bosch Center for Artificial Intelligence, Germany)
  • Shuming Shi (Tencent AI lab, China)