37.273, Confs: Software Mention Detection and Coreference Resolution Shared Task (NSLP at LREC 2026) (Spain)

[The LINGUIST List]

LINGUIST List: Vol-37-273. Tue Jan 20 2026. ISSN: 1069 - 4875.

Subject: 37.273, Confs: Software Mention Detection and Coreference Resolution Shared Task (NSLP at LREC 2026) (Spain)

Moderator: Steven Moran (linguist at linguistlist.org)
Managing Editor: Valeriia Vyshnevetska
Team: Helen Aristar-Dry, Mara Baccaro, Daniel Swanson
Jobs: jobs at linguistlist.org | Conferences: callconf at linguistlist.org | Pubs: pubs at linguistlist.org

Homepage: http://linguistlist.org

Editor for this issue: Valeriia Vyshnevetska <valeriia at linguistlist.org>

================================================================


Date: 19-Jan-2026
From: Sharmila Upadhyaya [sharmila.upadhyaya at gesis.org]
Subject: Software Mention Detection and Coreference Resolution Shared Task (NSLP at LREC 2026)


Software Mention Detection and Coreference Resolution Shared Task
(NSLP at LREC 2026)
Short Title: SOMD 2026

Date: 14-Jan-2026 - 12-May-2026
Location: Mallorca, Spain
Contact: Sharmila Upadhyaya
Contact Email: sharmila.upadhyaya at gesis.org
Meeting URL:
https://nfdi4ds.github.io/nslp2026/docs/somd_shared_task.html

Linguistic Field(s): Computational Linguistics
Subject Language(s): English (eng)

Submission Deadline: 27-Mar-2026

We would like to invite everyone to the third iteration of the
Software Mention Detection and Coreference Resolution (SOMD 2026)
shared task. Building on the success of the previous editions(SOMD
2024, SOMD 2025), this edition continues to focus on resolving
software mentions across scholarly documents.
We address the task of coreference resolution of software mentions
across multiple documents, i.e. given a set of software mentions
extracted from multiple scientific publications, related extracted
attributes as well as sentences in which these occur, cluster these
mentions so that all software mentions in a particular cluster refer
to the same real world software. We define three subtasks with varying
challenges:
Subtasks:
Subtask 1: Coreference Resolution over Gold Mentions
Given all gold-standard annotated software mentions (including
metadata and their sentences), the objective of this task is to
generate clusters in which each cluster represents mentions referring
to the same underlying software.
Subtask 2: Coreference Resolution over Predicted Mentions
In this subtask, we provide predicted software mentions and their
metadata, which are automatically extracted using a baseline model.
The challenge is to resolve all co-references to the same software by
creating clusters of mentions referring to the same software. This
reflects real-world co-reference resolution, where upstream pipelines
(such as entity and metadata extraction) are imperfect.
Subtask 3: Coreference Resolution at Scale
For this subtask, we provide predicted mentions of software and
metadata at a larger scale.  Participants are expected to resolve
coreferences to the same software by creating clusters of mentions
referring to the same software. Since there are many more entity
variants and numerous possible software identities in the provided
corpus, this increases the computational runtime challenge for the
coreference resolution task. This challenges models to scale
effectively, maintain accuracy, and distinguish among an increasingly
dense field of similar or overlapping software mentions.
Timeline:
 - Registration Opens: January 14 2026 (Codabench link (Subtask1,
Subtask2, Subtask3)
 - Train/Test Data Release (All Subtasks): January 20, 2026
 - Competition Phase: January 20 – February 20, 2026 (via Codabench)
 - System Paper & Code Submission Deadline: February 27, 2026
 - Notification of Acceptance: March 13, 2026
 - Camera-Ready Papers Due: March 27, 2026
 - Workshop Date: May 12, 2026
Workshop Venue:
SOMD 2026 will be held as part of NSLP 2026, co-located with LREC
2026, in Mallorca, Spain.
Participants in the shared task are invited to submit system
description papers detailing their methods and results. Accepted
system papers will be published in the official proceedings volume of
the workshop, which will be archived in the ACL Anthology.
For full task details, data access, and participation instructions,
please visit the shared task website:
https://nfdi4ds.github.io/nslp2026/docs/somd_shared_task.html.



------------------------------------------------------------------------------

********************** LINGUIST List Support ***********************
Please consider donating to the Linguist List, a U.S. 501(c)(3) not for profit organization:

https://www.paypal.com/donate/?hosted_button_id=87C2AXTVC4PP8

LINGUIST List is supported by the following publishers:

Bloomsbury Publishing http://www.bloomsbury.com/uk/

Cambridge University Press http://www.cambridge.org/linguistics

Cascadilla Press http://www.cascadilla.com/

De Gruyter Brill https://www.degruyterbrill.com/?changeLang=en

Edinburgh University Press http://www.edinburghuniversitypress.com

John Benjamins http://www.benjamins.com/

Language Science Press http://langsci-press.org

Lincom GmbH https://lincom-shop.eu/

MIT Press http://mitpress.mit.edu/

Multilingual Matters http://www.multilingual-matters.com/

Narr Francke Attempto Verlag GmbH + Co. KG http://www.narr.de/

Netherlands Graduate School of Linguistics / Landelijke (LOT) http://www.lotpublications.nl/

Peter Lang AG http://www.peterlang.com


----------------------------------------------------------
LINGUIST List: Vol-37-273
----------------------------------------------------------