20th Workshop on Innovative Use of NLP for Building Educational Applications

Quick Info
Co-located with	ACL 2025
Location	Vienna, Austria
Deadline	March 1, 2025
Date	July 31 and August 1, 2025
Organizers	Ekaterina Kochmar, Bashar Alhafni, Marie Bexte, Jill Burstein, Andrea Horbach, Ronja Laarmann-Quante, Anaïs Tack, Victoria Yaneva, Zheng Yuan
Contact	bea.nlp.workshop@gmail.com

Workshop Description

The BEA Workshop is a leading venue for NLP innovation in the context of educational applications. It is one of the largest one-day workshops in the ACL community with over 100 registered attendees in the past several years. The growing interest in educational applications and a diverse community of researchers involved resulted in the creation of the Special Interest Group in Educational Applications (SIGEDU) in 2017, which currently has over 400 members.

The workshop’s continuing growth reflects how technology is increasingly fulfilling societal demands. For instance, the BEA16 workshop in 2021 hosted a panel discussion on “New Challenges for Educational Technology in the Time of the Pandemic” addressing the pressing issues around COVID-19. Additionally, NLP has evolved to aid diverse learning domains, including writing, speaking, reading, science, and mathematics, as well as the related intra-personal (e.g., self-confidence) and inter-personal (e.g., peer collaboration) skills. Within these areas, the community continues to develop and deploy innovative NLP approaches for use in educational settings.

Another significant advancement in educational applications within the Computational Linguistics (CL) community is the continuing series of shared-task competitions organized by and hosted at the BEA workshop. Over the years, this initiative has included four dedicated tasks focused solely on grammatical error detection and correction. Moreover, NLP/Education shared tasks have expanded into novel research areas, such as the Automated Evaluation of Scientific Writing at BEA11, Native Language Identification at BEA12, Second Language Acquisition Modeling at BEA13, Complex Word Identification at BEA13, Generating AI Teacher Responses in Educational Dialogues at BEA18, and Automated Prediction of Item Difficulty and Item Response Time and Multilingual Lexical Simplification at BEA19. These competitions have significantly bolstered the visibility and interest in our field.

The 20th BEA will be the first edition of BEA as a 2-day workshop. It will adopt the same format as the 2024 edition and will be hybrid, integrating both in-person and virtual presentations and attendance. The workshop will feature a keynote talk, and a main workshop track with oral presentation sessions and large poster sessions to facilitate the presentation of a wide array of original research. Moreover, there will be a half-day tutorial, and a shared task comprising an oral overview presentation by the shared task organizers and several poster presentations by the shared task participants.

We expect that the workshop will continue to highlight novel technologies and opportunities, including the use of state-of-the-art large language models in educational applications, and challenges around responsible AI for educational NLP, in English as well as other languages.

Call for Papers

The workshop will accept submissions of both full papers and short papers, eligible for either oral or poster presentation. We solicit papers that incorporate NLP methods, including, but not limited to:

automated scoring of open-ended textual and spoken responses;
game-based instruction and assessment;
educational data mining;
use of generative AI in education and its impact;
intelligent tutoring;
collaborative learning environments;
peer review;
grammatical error detection and correction;
learner cognition;
spoken dialog;
multimodal applications;
annotation standards and schemas;
tools and applications for classroom teachers, learners, or test developers; and
use of corpora in educational tools.

Important Dates

All deadlines are 11:59pm UTC-12 (anywhere on earth). Note that at this point some of the deadlines are tentative and may be adjusted later.

Event	Date
Submission Deadline	March 1, 2025
Notification of Acceptance	April 17, 2025
Camera-ready Papers Due	May 16, 2025
Pre-recorded Videos Due	July 7, 2025
Workshop	July 31 and August 1, 2025

Submission Guidelines

To streamline the submission process, we rely on the ACL submission guidelines and the START conference system. All submissions undergo review by the program committee.

Long, Short, and Demo Papers: Authors can choose to submit long papers (up to eight (8) pages) or short papers (up to four (4) pages), alongside unlimited references. After peer review, all accepted papers will be allotted an additional page of content (up to nine for long papers, five for short papers), allowing authors to address reviewer comments. Authors are strongly urged to present a live demonstration for papers that elaborate on systems. If opting for this, authors should choose either “long paper + demo” or “short paper + demo” under the “Submission Category” on the submission page.
LaTeX and Word Templates: Authors must ensure their paper submissions adhere to the general paper formatting guidelines for “*ACL” conferences, found here, and use the official ACL style templates, downloadable here. Do not modify these style files or use templates intended for other conferences. Submissions failing to meet required styles, including paper size, margin width, and font size restrictions, will be rejected without review.
Limitations: Authors are required to discuss the limitations of their work in a dedicated section titled “Limitations”. This section should be included at the end of the paper, before the references, and it will not count toward the page limit. This includes both long and short papers. Note, prior to the December 2023 cycle, this was optional.
Ethics Policy: Authors are required to honour the ethical code set out in the ACL Code of Ethics. The consideration of the ethical impact of our research, use of data, and potential applications of our work has always been an important consideration, and as artificial intelligence is becoming more mainstream, these issues are increasingly pertinent. We ask that all authors read the code, and ensure that their work is conformant to this code. Authors are encouraged to devote a section of their paper to concerns about the ethical impact of the work and to a discussion of broader impacts of the work, which will be taken into account in the review process. This discussion may extend into a 5th page (short papers) or 9th page (long papers).
Anonymity: Given the blind review process, it is essential to ensure that papers remain anonymous. Authors should avoid self-references that disclose their identity (e.g., “We previously showed (Smith, 1991)”), opting instead for citations like “Smith previously showed (Smith, 1991)”.
Conflicts of Interest: Authors are required to mark potential reviewers who have co-authored the paper, belong to the same research group or institution, or have had prior exposure to the paper, ensuring transparency in the review process.
Double Submissions: We adhere to the official ACL double-submission policy. If papers are submitted to both BEA and another conference or workshop, authors must specify the other event on the title page (as a footnote on the abstract). Additionally, the title page should state that if the paper is accepted for presentation at BEA, it will be withdrawn from other conferences and workshops.
Republications: Previously published papers will not be accepted.

Presentation Guidelines

All accepted papers must be presented at the workshop to appear in the proceedings. The workshop will include both in-person and virtual presentation options. At least one author of each accepted paper must register for the conference by the early registration deadline.

Long and short papers will be presented orally or as posters as determined by the workshop organizers. While short papers will be distinguished from long papers in the proceedings, there will be no distinction in the proceedings between papers presented orally and papers presented as posters.

If you are interested in sharing your code and data with the BEA community, we created the #bea-workshop topic on GitHub.

Shared Task

In addition to the main track, the workshop will host a shared task on Pedagogical Ability Assessment of AI-powered Tutors. For more information on how to participate and latest updates, please refer to the shared task website.

Pedagogical Ability Assessment of AI-powered Tutors

Tutorial

We will also host a half-day tutorial on LLMs for Education: Understanding the Needs of Stakeholders, Current Capabilities and the Path Forward.

LLMs for Education: Understanding the Needs of Stakeholders, Current Capabilities and the Path Forward

Organizers: Sankalan Pal Chowdhury (ETH Zurich), Nico Daheim (TU Darmstadt), Ekaterina Kochmar (MBZUAI), Jakub Macina (ETH Zurich), Donya Rooein (Bocconi University), Mrinmaya Sachan (ETH Zurich), and Shashank Sonkar (Rice University).
Description: This tutorial will aim to bridge the gap between NLP researchers and Artificial Intelligence in Education (AIED) practitioners to help participants understand the requirements and challenges of education, enabling them to develop LLMs that align with educational needs, and to enable educators to gain a deeper understanding of the capabilities and limitations of current NLP technologies, fostering effective integration of LLMs in educational contexts.

Invited Talk

Kostia Omelianchuk, Grammarly

Details to follow

Participation

Registration

TBD

Visa information