1st Call For Participation: Automatic Minuting Shared Task - AutoMin @ SIGDIAL 2025

TG
Tirthankar Ghosal
Mon, Mar 10, 2025 3:45 PM

Third Run of the Automatic Minuting Shared Task - AutoMin @ SIGDIAL 2025
A great opportunity to assess LLMs' ability to summarize and retrieve
information from long contextsWe propose AutoMin 2025, the third instance
of bi-annual shared task on meeting summarization into structured meeting
minutes. We build upon our past experience from two previous AutoMins and
add a new challenge to facilitate personalized access: answering questions
about meeting content.As in the previous editions, the tasks are run in
English and Czech while the new question-answering task will be run
monolingually (English-only) and cross-lingually (Czech questions about
English meetings).This challenge is highly relevant for assessing LLMs'
ability to summarize and retrieve information from long contexts,
equivalent to the length of an hour-long meeting.A dedicated workshop is
scheduled for August 28th, 2025, as part of SIGDIAL 2025:
https://2025.sigdial.org. Challenge Websiteh
ttps://ufal.github.io/automin-2025/  TasksWe propose two main tasks.

  • Task A (minuting): The task consists of automatically creating minutes
    from multiparty meeting transcripts. The generated minute would be
    evaluated both via automatic and manual metrics.
  • Task B (question answering): The task consists in answering questions
    based on meeting transcripts. For this challenge, participants will be
    tasked with answering these questions either monolingually (English
    questions on English transcripts) or cross-lingually (Czech questions on
    English transcripts). Answers will be evaluated using a LLM-as-a-judge
    metric.

Participant registrationAll participants should register using the following
link
https://docs.google.com/forms/d/e/1FAIpQLSeMTa2DkXtZCMbBpTo5c853nOr3yq2N1dXExPim0sMZlWyzKQ/viewform
Important Dates
Registration and CfP From March 1st, 2025
Training and Dev Data Available March 1st, 2025
Test Data Available April 15th, 2025
System Run and Output Submission April 29th, 2025
System Paper Submission May 5th, 2025
Result Announcement May 22d, 2025
Acceptance Notification of System Papers June 2025 (TBA)
Camera Ready for System Papers TBA
Event Date August 28th, 2025
PublicationAll teams will be required to submit a brief technical report
describing their method. Details will be given on the challenge website
soon. OrganizersLaurent Besacier, Naver Labs Europe, FranceOndřej Bojar,
UFAL, Charles University, Czech RepublicTirthankar Ghosal, Oak Ridge
National Laboratory, USAMarie Hledıkova, UFAL, Charles University, Czech
RepublicThibaut Thonet, Naver Labs Europe, France
ContactThe organizers can be contacted via the following email address:
automin@ufal.mff.cuni.cz

--

+++++++++++++++++++++++++++++++++++

Tirthankar Ghosal

Scientist (NLP/AI and HPC)
https://www.ornl.gov/staff-profile/tirthankar-ghosal

National Center for Computational Sciences (NCCS)

Oak Ridge National Laboratory, United States

&

Adjunct Faculty (NLP/AI)
https://bredesencenter.utk.edu/faculty/tirthankar-ghosal/

University of Tennessee Knoxville

United States

++++++++++++++++++++++++++++++++++++

*Third Run of the Automatic Minuting Shared Task - AutoMin @ SIGDIAL 2025* A great opportunity to assess LLMs' ability to summarize and retrieve information from long contextsWe propose AutoMin 2025, the third instance of bi-annual shared task on meeting summarization into structured meeting minutes. We build upon our past experience from two previous AutoMins and add a new challenge to facilitate personalized access: answering questions about meeting content.As in the previous editions, the tasks are run in English and Czech while the new question-answering task will be run monolingually (English-only) and cross-lingually (Czech questions about English meetings).This challenge is highly relevant for assessing LLMs' ability to summarize and retrieve information from long contexts, equivalent to the length of an hour-long meeting.A dedicated workshop is scheduled for August 28th, 2025, as part of SIGDIAL 2025: https://2025.sigdial.org. Challenge Websiteh ttps://ufal.github.io/automin-2025/ TasksWe propose two main tasks. - Task A (minuting): The task consists of automatically creating minutes from multiparty meeting transcripts. The generated minute would be evaluated both via automatic and manual metrics. - Task B (question answering): The task consists in answering questions based on meeting transcripts. For this challenge, participants will be tasked with answering these questions either monolingually (English questions on English transcripts) or cross-lingually (Czech questions on English transcripts). Answers will be evaluated using a LLM-as-a-judge metric. Participant registrationAll participants should register using the following link <https://docs.google.com/forms/d/e/1FAIpQLSeMTa2DkXtZCMbBpTo5c853nOr3yq2N1dXExPim0sMZlWyzKQ/viewform> Important Dates Registration and CfP From March 1st, 2025 Training and Dev Data Available March 1st, 2025 Test Data Available April 15th, 2025 System Run and Output Submission April 29th, 2025 System Paper Submission May 5th, 2025 Result Announcement May 22d, 2025 Acceptance Notification of System Papers June 2025 (TBA) Camera Ready for System Papers TBA Event Date August 28th, 2025 PublicationAll teams will be required to submit a brief technical report describing their method. Details will be given on the challenge website soon. OrganizersLaurent Besacier, Naver Labs Europe, FranceOndřej Bojar, UFAL, Charles University, Czech RepublicTirthankar Ghosal, Oak Ridge National Laboratory, USAMarie Hledıkova, UFAL, Charles University, Czech RepublicThibaut Thonet, Naver Labs Europe, France ContactThe organizers can be contacted via the following email address: automin@ufal.mff.cuni.cz -- +++++++++++++++++++++++++++++++++++ *Tirthankar Ghosal* Scientist (NLP/AI and HPC) <https://www.ornl.gov/staff-profile/tirthankar-ghosal> National Center for Computational Sciences (NCCS) Oak Ridge National Laboratory, United States & Adjunct Faculty (NLP/AI) <https://bredesencenter.utk.edu/faculty/tirthankar-ghosal/> University of Tennessee Knoxville United States ++++++++++++++++++++++++++++++++++++