First Call for Papers
The 5th Multilingual Representation Learning (MRL) workshop (https://sigtyp.github.io/ws2025-mrl.html) will be co-located with EMNLP 2025 in Suzhou, China. We invite your submissions with a deadline of August 23, 2025 (AoE).
Submission Details
We welcome submissions in the following formats:
- Extended Abstracts (up to 2 pages): Non-archival submissions.
- Papers (4-8 pages): Authors can decide whether their submission is archival or non-archival. We encourage longer papers (more than 4 pages) to opt for archival submission.
- ARR Submissions: We accept papers previously submitted to ARR. Papers must have been submitted to the ARR May 2025 cycle or an earlier cycle and have received reviews and a meta review.
All submissions must not have been previously published in an archival venue.
Formatting: Submissions must be anonymous and must follow the ACL template (LaTeX and Word formats available). The Overleaf template is available at:
https://www.overleaf.com/latex/templates/association-for-computational-l...
Submission portal: https://openreview.net/group?id=EMNLP/2025/Workshop/MRL
Reviewer Sign-Up
If you would like to sign up to be a reviewer for MRL, please fill in this form: https://forms.gle/fbizvGghD33cP3HP7
Important Dates
Direct Submission Deadline: Aug 23, 2025 (AoE)
ARR Submission Deadline: Sep 23, 2025 (AoE)
Acceptance Notification: Oct. 1, 2025 (AoE)
Camera-ready Deadline: Oct. 14, 2025 (AoE)
Workshop Date: TBD, from November 5-9, 2025
About MRL 2025
Multilingual representation learning methods have proven to be extremely efficient for transfer learning between languages, and they demonstrate potential in adapting natural language processing (NLP) models to languages or tasks with little to no training resources. On the other hand, there are many aspects of such models that have potential for further development and analysis in order to prove their applicability in various contexts. These contexts include different NLP tasks and also understudied language families, which face important obstacles in achieving practical advances that could improve the state-of-the-art in NLP for various low-resource or underrepresented languages.
We present the fifth edition of the Workshop on Multilingual Representation Learning (MRL), which brings together an interdisciplinary community of researchers working on different aspects of multilingual representation learning methods, providing the rapidly growing number of researchers working on the topic with a means of communication and an opportunity to present their work and exchange ideas. The main objectives of the workshop are:
- To construct and present a wide array of multilingual representation learning methods, including their theoretical formulation and analysis, practical aspects such as the application of current state-of-the-art approaches in transfer learning to different tasks, or studies on adaptation into previously under-studied contexts;
- To provide a better understanding on how language typology may impact the applicability of these methods and motivate the development of novel methods that are more generic or competitive in different languages;
- To promote collaborations in developing novel software libraries and benchmarks for implementing or evaluating multilingual models that would accelerate progress in the field.