Call for System Demonstrations
Important Dates
All deadlines are 11:59PM UTC-12:00 (“anywhere on Earth”).
Submissions due | September 30, 2024 |
Notifications | November 29, 2024 |
Camera-ready papers due | December 15, 2024 |
Conference | January 19-24, 2025 |
Invitation for Submission
The COLING 2025 Demonstration Program Committee invites proposals for system demonstrations, which can range from early prototypes to mature systems. The demonstration program is part of the main conference program and aims at showcasing working systems that address a wide range of conference topics. The session will provide opportunities to exchange ideas gained from the practical implementation of NLP systems and to obtain feedback from expert users.
All accepted demos are published in a companion volume of the conference proceedings. We expect at least one of the authors to present a live demo during a demo session at COLING 2025, with an accompanying poster.
COLING 2025 will be held in Abu Dhabi from January 19th to 24th, 2025.
The COLING conference has a history that dates back to the 1960s, and regularly attracts more than 700 delegates. The conference has developed into one of the premier Computational Linguistics (CL) and Natural Language Processing (NLP) conferences worldwide and is a major international event for the presentation of new research results and for the demonstration of new systems and techniques in the broad field of CL and NLP.
Topics of Interest
COLING 2025 solicits demonstrations on original and unpublished research on topics, including, but not limited to:
- Dialogue and Interactive Systems
- Discourse and Pragmatics
- Document Classification and Topic Modeling
- Ethics, Bias, and Fairness
- Information Extraction
- Information Retrieval and Text Mining
- Interpretability and Analysis of Models for NLP
- Language Modeling
- Language Resources and Evaluation
- Linguistic Insights Derived using Computational Techniques
- Linguistic Theories, Cognitive Modeling and Psycholinguistics
- Low-Resource and Efficient Methods for NLP
- Machine Learning for Computational Linguistics and NLP
- Machine Translation and Translation Aids
- Multilingualism and Language Diversity
- Multimodal and Grounded Language Acquisition
- NLP and LLM Applications (such as Education, Healthcare, Finance, Legal NLP, Computational Social Science, etc.)
- Natural Language Generation
- Offensive Speech Detection and Analysis
- Phonology, Morphology and Word Segmentation
- Question Answering
- Lexical Semantics
- Sentence-level Semantics (Textual Inference, Paraphrasing, etc)
- Sentiment Analysis, Stylistic Analysis, Opinion and Argument Mining
- Speech Recognition and Synthesis, and Spoken Language Understanding
- Summarization and Simplification
- Syntactic analysis (tagging, chunking, parsing)
- Vision and Robotics
Papers targeting any of these topics from the perspective of the Sustainability Goals of the UN are especially welcome.
Submitted systems may be of the following types:
- Natural Language Processing systems or system components
- Application systems using language technology components
- Software tools or API for computational linguistics research
- Software for evaluating natural language processing systems
- Software supporting learning or education
- Tools for data visualization and annotation
- Open-sourced large language models and their applications
- Development tools
Please note: Commercial products and services are welcome; however, sales and marketing activities are not appropriate in the Demonstrations Program.
Submissions
The submissions should address the following questions:
- What problem does the proposed system address?
- Why is the system important and what is its impact?
- What is the novel 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?
There are two parts to the submission, the paper and a video.
Paper
The maximum submission length is 6 pages, but with extra space for an optional ethics/broader impact statement (only necessary if you think you may want to preempt reviewer questions, given the conference’s ethics policy), unlimited pages for references and an unlimited appendix. Accepted papers will be given one additional page of content so that reviewers’ comments can be taken into account.
Papers must be submitted in English and must conform to the official COLING 2025 templates available from the link below; the only acceptable format for submissions is PDF. Your paper does not need to be anonymous (see Reviewing Policy). Any papers that do not follow the official style guidelines and page limits will be automatically rejected.
Authors should follow the general instructions for COLING 2025 proceedings, which are an adaptation of the general instructions for *ACL proceedings.
To prepare your submission, please make sure to use the COLING 2025 style files available here:
Video
A short (max. 2 minutes) video demonstrating the system. This video will be used to evaluate the paper but won’t be published unless requested.
- A screencast with audio narration is a natural choice for demos that can be presented on a screen. Otherwise, a video of a user interacting with the system can be used.
- The production quality of the video is not of interest. Hence, we encourage the videos to be simply a screencast of the software that is getting demoed, with zero to minimal editing efforts.
- We recommend that you publish your video to YouTube or another website and include the link in your paper. If you prefer not to publicly upload a screencast, please submit the video (in MP4 format) as supplementary material when you submit your paper.
How to Submit
Submission and reviewing will be managed in the START system.
Ethics
COLING 2025 adopts the ACL Ethics Policy.
Multiple Submission Policy
Papers which are submitted to the COLING 2025 demo session cannot be under review for other conferences or journals at the same time, or for other tracks at COLING 2025 (e.g. the main session). In addition, we will not consider any paper that overlaps significantly in content or results with papers that will be (or have been) published elsewhere. Submissions that violate these requirements will be desk rejected.
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. Relevant papers that meet formatting requirements will be assessed on the basis of their relevance to the demo track, contribution, clarity, completeness, and novelty.
Demo Session Chairs
Contact email: coling2025demos@googlegroups.com
- Mark Dras, Macquarie University
- Brodie Mather, Florida Institute for Human & Machine Cognition