Call for Papers

EIKE addresses the growing need for advanced methods to extract and represent knowledge embedded in unstructured and multimodal data, with a particular emphasis on socially relevant contexts. Traditional pipelines often overlook nuanced information, such as presuppositions, causal assumptions, and tacit inferences, which are critical for understanding emotional undertones, societal themes, and cultural norms. This workshop focuses on integrating machine learning models (e.g., LLMs) and ontology-driven frameworks to directly infer semantically rich graphs from multimodal data, advancing the fields of Entity Linking (EL) and Information Retrieval (IR). By embracing neuro-symbolic AI and ethical considerations, EIKE aims to drive innovation in creating scalable and explainable systems for real-world applications.

Topic Areas

Knowledge Extraction and Information Extraction: Techniques for identifying and representing explicit and tacit context-dependent knowledge embedded in unstructured and multimodal data sources, with an emphasis on socially relevant insights.
Machine reading and multimodal machine understanding: Exploring models and methodologies that employ a graph representation to represent knowledge from text and multimodal sources.
Ontology-Driven contextualization: Integrating ontologies to ground implicit and explicit knowledge in structured and interpretable frameworks.
Neural, symbolic and neuro-symbolic approaches for EL and IR: Neural, symbolic and combined approaches for richer, more accurate entity linking and information retrieval.
Semantics of implicit knowledge systems: What truth and modal operators underlie implicit knowledge axioms in neuro-symbolic systems?
Ethics of implicit knowledge systems: Addressing the transparency, biases, and societal implications of extracting and operationalizing social and human-focused knowledge.
Practical applications: Case studies in domains such as healthcare, legal systems, and cultural heritage that highlight the benefits of knowledge extraction for socially attuned applications.

Guidelines and Review Criteria

The following contribute categories are welcome:

Full Papers (13 pages including references)
Short Papers (6 pages including references)
Position Papers (2-3 pages excluding references, not included in the proceedings)
Extended Abstracts of recently published papers (2-3 pages excluding references, not included in the proceedings)

We welcome any types of research, resource and application papers, as well as (short only) demonstration submissions. Submissions must be sent via Easychair and should be formatted in CEUR-WS single-column format (template available on workshop website).

For inclusion in the workshop, at least one of the authors of accepted papers needs to register at FOIS 2025 and participate on-site at EIKE.

How to Submit

All papers must be submitted non-anonymously in PDF format following the CEUR-WS single-column formatting guidelines.
The direct template download for Latex and MS Word is available here: http://ceur-ws.org/Vol-XXX/CEURART.zip
There is also an Overleaf Template available here: LaTex Template
Papers must be submitted through the EasyChair system. Submissions should be made in PDF through EasyChair following the link (select track WS: Explicit and Implicit Knowledge Extraction from Text)
Papers accepted at EIKE workshops will be published in a volume of CEUR workshop JOWO proceedings.

Important Dates

Submission Deadline: May 25, 2025
Author Notification: July 14, 2025
Camera Ready Version: September 1, 2025
Workshop Date: September 8 or 9, 2025

Page updated

Google Sites

Report abuse