Call for Papers

*2nd International Workshop on Natural Scientific Language Processing and Research Knowledge Graphs (NSLP 2025)*

01 or 02 June 2025 (tbc) Portoroz, Slovenia (NSLP 2025 is co-located with ESWC 2025)

https://nfdi4ds.github.io/nslp2025/

Scientific research is almost exclusively published in unstructured text formats, which are not readily machine-readable. While technological approaches can help to get this flood of scientific information and new knowledge under control, the development of such technologies is very complex in practice and hinders the creation of infrastructures and systems to track research and assist the scientific community with applications such as dedicated scientific search engines and recommender systems. The 2nd International Workshop on Natural Scientific Language Processing and Research Knowledge Graphs (NSLP) aims to bring together researchers working on the processing, analysis, transformation and exploitation of scientific language and research knowledge graphs including all relevant sub-topics. NSLP 2025 is a full-day workshop co-located with ESWC 2025 to be held in Portoroz, Slovenia on 01 or 02 June 2025 (to be confirmed).

*Topics of interest include, but are not limited to* • Research/Scientific Knowledge Graphs (RKGs/SKGs) and other forms of structured scientific knowledge representation • Information Extraction for RKGs/SKGs • Question Answering over RKGs/SKGs • Other types of usage of RKGs/SKGs for downstream applications • Scientific LLMs: LLMs for Natural Scientific Language Processing (NSLP) • NSLP (monolingual, cross-lingual, multilingual) • Language Resources and Language Technologies for NSLP • Domain-specific Adaptation of NSLP Methods • Information Extraction from Scholarly Publications • Classification of Scholarly Publications (document collections, individual documents, parts of documents) • Summarisation of Scholarly Publications • Scholarly Information Retrieval and Scientific Search Engines • Digital Libraries of Scholarly Information • Bibliometrics and Scientometrics • Micropublications and Nanopublications

*Important Dates* • Paper submission deadline: 06 March 2025 • Notification of acceptance: 03 April 2025 • Camera-ready submission: 17 April 2025 • Workshop: 01 or 02 June 2025 (tbc)

*Submissions*

The NSLP 2025 workshop invites submissions of regular long papers, position papers, and short papers presenting negative results, in-progress projects, and demos. We especially encourage submissions from junior researchers and students from diverse backgrounds.

• The workshop invites anonymous submissions of regular long papers (up to 15 pages without references and appendix) and short papers (up to 8 pages without references and appendix) presenting negative results, in-progress projects, and demos. In both categories, position papers can be submitted as well. • Authors are permitted to include an optional appendix of up to 2 pages. However, reviewers will not be mandated to review the appendix; all papers must be self-contained. • Reviewing will be performed double-blind. Reviewers will not actively try to identify the authors. • Submissions must be in PDF, formatted in the style of the Springer Publications format for Lecture Notes in Computer Science (LNCS). • The proceedings of this workshop will be published as an Open Access volume in the Springer series Lecture Notes in Artificial Intelligence (LNAI), fully sponsored by the NFDI4DS project. • At least one author per contribution must register for the conference for presentation as ESWC 2025 (including all workshops) is an in-person event. • We will not accept work that is under review or has already been published in or accepted for publication in a journal, another conference, or another workshop. • All submissions are done via EasyChair: https://easychair.org/conferences?conf=nslp2025

*Keynote Speaker* Michele Pasin, Digital Science, UK

*Shared Tasks * NSLP 2025 offers three shared tasks:

1. MESD: Metadata Extraction from Scholarly Documents 2. ReadMe2KG: Github ReadMe to Knowledge 3. FoRC: Field of Research Classification

*Shared Task 1: MESD: Metadata Extraction from Scholarly Documents* The MESD shared task aims to improve metadata extraction from scholarly publications to enhance their FAIRness (Findability, Accessibility, Interoperability, Reusability). Given training data of 500 labelled scientific documents along with their extracted text, participants are asked to develop models that output metadata of nine predefined labels. A label-free test set of 100 samples will be released for final evaluation, where systems will be ranked based on F1 score using Levenshtein Similarity (≥90%).

Organiser: Zeyd Boukhers (Fraunhofer FIT)

Important dates:

• Release of training datasets: January 27, 2025 • Release of testing datasets: February 15, 2025 • Deadline for system submissions: February 22, 2025 • Announcement of results: February 27, 2025 • Paper submission deadline: March 6, 2025 • Notification of acceptance: April 3, 2025 • Camera-ready submission: April 17, 2025

*Shared Task 2: ReadMe2KG: Github ReadMe to Knowledge Graph* The ReadMe2KG shared task focuses on fine-grained Named Entity Recognition (NER) in GitHub README files to enhance the NFDI4DS knowledge graph. Participants will develop classifiers to identify 10 entity types, including “Dataset,” “Software,” and “Publication,” from a dataset of approximately 160 README files. The task aims to improve the integration of research-related metadata from GitHub repositories into the research data lifecycle.

Organisers: Genet Asefa Gesese (FIZ Karlsruhe), Zongxiong Chen (Fraunhofer FOKUS), Shufan Jiang (FIZ Karlsruhe), Mary Ann Tan (FIZ Karlsruhe), Sonja Schimmler (Fraunhofer FOKUS)

Important dates:

• Release of training datasets: January 25, 2025 • Release of testing datasets: February 15, 2025 • Deadline for system submissions: February 22, 2025 • Announcement of results: February 27, 2025 • Paper submission deadline: March 6, 2025 • Notification of acceptance: April 3, 2025 • Camera-ready submission: April 17, 2025

*Shared Task 3: FoRC: Field of Research Classification* The FoRC shared task aims to classify scientific documents into (sub-)topics according to a predefined schema. The second iteration of the task (see NSLP 2024 for the first) will focus on classifying computational linguistics publications taken from the ACL Anthology using the FoRC4CL data and taxonomy. Weakly supervised data will be added to FoRC4CL to create a bigger training corpus for classifying publications into 170 (sub-)topics of the field of computational linguistics.

Organisers: Maria Francis (DFKI; University of Trento), Raia Abu Ahmad (DFKI), Ekaterina Borisova (DFKI), Georg Rehm (DFKI)

Important dates:

• Release of training and testing data: February 18, 2025 • Deadline for system submissions: March 25, 2025 • Paper submission deadline: March 27, 2025 • Notification of acceptance: April 10, 2025 • Camera-ready submission: April 17, 2025

The NSLP 2025 website provides more information on the shared tasks: https://nfdi4ds.github.io/nslp2025/

*Organisers of NSLP 2025* • Georg Rehm, DFKI & HU Berlin, Germany • Sonja Schimmler, TU Berlin & Fraunhofer FOKUS, Germany • Stefan Dietze, GESIS & HHU Düsseldorf, Germany • Natalia Manola, OpenAIRE, Greece

*Contact*

Georg Rehm georg.rehm@dfki.de