[Corpora-List] Shared tasks on acronym extraction and disambiguation (Deadline: Nov. 10, 2021) at the second AAAI workshop on scientific document understanding

SDU AAAI21 sdu.aaai21 at gmail.com
Thu Sep 16 01:40:58 CEST 2021

The AAAI-22 Workshop on Scientific Document Understanding (SDU at AAAI-22) invites you to participate in two shared tasks on acronym extraction and disambiguation in multilingual scientific and legal documents. The participants of the shared tasks are invited to the workshop and will present their work in the shared-task session. The winner and the selected teams (based on the substance of the approach and analysis) will be provided with an oral presentation. In addition, SDU at AAAI-22 strongly encourages participants to submit their system reports to be published in the workshop proceedings under the shared task track.


Acronym Extraction: In this task, the goal is to detect the acronyms and

their expanded form mentioned in English, French, Spanish, Danish, Persian,

and Vietnamese text. Participants are provided with manually labeled

training and development datasets consisting of 4,000 English, 1,000

Persian, and 800 Vietnamese paragraphs in the scientific domain and 4,000

English, 8,000 French, 6,400 Spanish, and 3,000 Danish paragraphs in the

legal domain. For more information on this task (including the baseline and

scoring), please check out our website

<https://sites.google.com/view/sdu-aaai22/shared-task> and the

corresponding GitHub

<https://github.com/amirveyseh/AAAI-22-SDU-shared-task-1-AE> and CodaLab

<https://competitions.codalab.org/competitions/34925> pages.


Acronym Disambiguation: The goal of this task is to identify the correct

long form of an ambiguous acronym from a list of possible long forms for

the given acronym in English, French and Spanish text. participants are

provided with the training and development datasets in English (both

scientific and legal domain), Spanish, and French consisting of 457 English

Scientific, 273 English legal, 493 Spanish, and 609 French acronyms. For

more information on this task (including the baseline and scoring), please

check out our website

<https://sites.google.com/view/sdu-aaai22/shared-task?authuser=0> and

the corresponding GitHub

<https://github.com/amirveyseh/AAAI-22-SDU-shared-task-2-AD> and CodaLab

<https://competitions.codalab.org/competitions/34899> pages.

Participants can submit their results to the corresponding CodaLab competitions for Acronym Extraction <https://competitions.codalab.org/competitions/34925> and Acronym Disambiguation <https://competitions.codalab.org/competitions/34899>. For more information on participation and system reports please check out our website <https://sites.google.com/view/sdu-aaai22/shared-task?authuser=0>.




Training and development set release: September 10, 2021

Test set release: November 1, 2021

System runs due date: November 10, 2021

System reports due date: November 20, 2021

SDU workshop at AAAI 2022: February 28 or March 1, 2022

All deadlines are 23:59 “anywhere on earth” (UTC-12)

If you have any questions, feel free to send your inquiries to sdu-aaai22 at googlegroups.com

For more updates, please follow us at Twitter: https://twitter.com/sdu_aaai22 and join the public group of the shared tasks: https://groups.google.com/g/SDU-AAAI22_PublicGroup

We look forward to your participation!



Thien Huu Nguyen, University of Oregon, USA


Walter Chang, Adobe Research, USA


Amir Pouran Ben Veyseh, University of Oregon, USA


Viet Dac Lai, University of Oregon, USA,


Franck Dernoncourt, Adobe Research, USA

Best regards,

SDU at AAAI-22 organizers -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 17177 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20210915/3675a3dd/attachment.txt>

More information about the Corpora mailing list