@inproceedings{upadhyaya-etal-2025-somd2025,
title = "{SOMD}2025: A Challenging Shared Tasks for Software Related Information Extraction",
author = {Upadhyaya, Sharmila and
Otto, Wolfgang and
Kr{\"u}ger, Frank and
Dietze, Stefan},
editor = "Ghosal, Tirthankar and
Mayr, Philipp and
Singh, Amanpreet and
Naik, Aakanksha and
Rehm, Georg and
Freitag, Dayne and
Li, Dan and
Schimmler, Sonja and
De Waard, Anita",
booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sdp-1.13/",
doi = "10.18653/v1/2025.sdp-1.13",
pages = "137--145",
ISBN = "979-8-89176-265-7",
abstract = "The use of software in acquiring, analyzing, and interpreting research data underscores its role as an essential artifact of scientific inquiry.Understanding and tracing the provenance of software in research helps in reproducible and collaborative research works.In this paper, we present an overview of our second iteration of the \textbf{So}ftware \textbf{M}ention \textbf{D}etection (SOMD) shared task as a part of the Scholarly Document Processing (SDP) workshop, that will be held in conjunction with ACL in 2025. We intend to foster among participants to brainstorm for optimized software mention detection and additional attributes and relation extraction tasks in the provided gold standard benchmark. Our shared task has two phases of challenges. First, the participants focus on implementing a joint framework for NER and RE for the given dataset. At the same time, the second phase includes the out-of-distribution dataset to evaluate the generalizability of the methods proposed in Phase I. The competition (March-April 2025) attracted 18 participants and spanned two months. Four teams have finished the competition and submitted full system descriptions. Participants applied various approaches, including joint and pipeline models, and explored data augmentation with LLM-generated samples.The evaluation was based on a macro-F1 score for both NER and RE, with the average reported as the SOMD-score.The winning teams achieved a SOMD-score of 0.89 in Phase I and 0.63 in Phase II, demonstrating the challenge of generalization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="upadhyaya-etal-2025-somd2025">
<titleInfo>
<title>SOMD2025: A Challenging Shared Tasks for Software Related Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sharmila</namePart>
<namePart type="family">Upadhyaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Otto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Krüger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Dietze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanpreet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">De Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-265-7</identifier>
</relatedItem>
<abstract>The use of software in acquiring, analyzing, and interpreting research data underscores its role as an essential artifact of scientific inquiry.Understanding and tracing the provenance of software in research helps in reproducible and collaborative research works.In this paper, we present an overview of our second iteration of the Software Mention Detection (SOMD) shared task as a part of the Scholarly Document Processing (SDP) workshop, that will be held in conjunction with ACL in 2025. We intend to foster among participants to brainstorm for optimized software mention detection and additional attributes and relation extraction tasks in the provided gold standard benchmark. Our shared task has two phases of challenges. First, the participants focus on implementing a joint framework for NER and RE for the given dataset. At the same time, the second phase includes the out-of-distribution dataset to evaluate the generalizability of the methods proposed in Phase I. The competition (March-April 2025) attracted 18 participants and spanned two months. Four teams have finished the competition and submitted full system descriptions. Participants applied various approaches, including joint and pipeline models, and explored data augmentation with LLM-generated samples.The evaluation was based on a macro-F1 score for both NER and RE, with the average reported as the SOMD-score.The winning teams achieved a SOMD-score of 0.89 in Phase I and 0.63 in Phase II, demonstrating the challenge of generalization.</abstract>
<identifier type="citekey">upadhyaya-etal-2025-somd2025</identifier>
<identifier type="doi">10.18653/v1/2025.sdp-1.13</identifier>
<location>
<url>https://aclanthology.org/2025.sdp-1.13/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>137</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SOMD2025: A Challenging Shared Tasks for Software Related Information Extraction
%A Upadhyaya, Sharmila
%A Otto, Wolfgang
%A Krüger, Frank
%A Dietze, Stefan
%Y Ghosal, Tirthankar
%Y Mayr, Philipp
%Y Singh, Amanpreet
%Y Naik, Aakanksha
%Y Rehm, Georg
%Y Freitag, Dayne
%Y Li, Dan
%Y Schimmler, Sonja
%Y De Waard, Anita
%S Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-265-7
%F upadhyaya-etal-2025-somd2025
%X The use of software in acquiring, analyzing, and interpreting research data underscores its role as an essential artifact of scientific inquiry.Understanding and tracing the provenance of software in research helps in reproducible and collaborative research works.In this paper, we present an overview of our second iteration of the Software Mention Detection (SOMD) shared task as a part of the Scholarly Document Processing (SDP) workshop, that will be held in conjunction with ACL in 2025. We intend to foster among participants to brainstorm for optimized software mention detection and additional attributes and relation extraction tasks in the provided gold standard benchmark. Our shared task has two phases of challenges. First, the participants focus on implementing a joint framework for NER and RE for the given dataset. At the same time, the second phase includes the out-of-distribution dataset to evaluate the generalizability of the methods proposed in Phase I. The competition (March-April 2025) attracted 18 participants and spanned two months. Four teams have finished the competition and submitted full system descriptions. Participants applied various approaches, including joint and pipeline models, and explored data augmentation with LLM-generated samples.The evaluation was based on a macro-F1 score for both NER and RE, with the average reported as the SOMD-score.The winning teams achieved a SOMD-score of 0.89 in Phase I and 0.63 in Phase II, demonstrating the challenge of generalization.
%R 10.18653/v1/2025.sdp-1.13
%U https://aclanthology.org/2025.sdp-1.13/
%U https://doi.org/10.18653/v1/2025.sdp-1.13
%P 137-145
Markdown (Informal)
[SOMD2025: A Challenging Shared Tasks for Software Related Information Extraction](https://aclanthology.org/2025.sdp-1.13/) (Upadhyaya et al., sdp 2025)
ACL