Tenth International Workshop on Narrative Extraction from Texts
held in conjunction with the 49th European Conference on Information Retrieval
Narratives increasingly shape how information is created, interpreted and shared. They influence public discourse, decision-making, journalism, and human-AI interaction, while evolving dynamically across textual, multimodal, and interactive settings. Understanding such narratives requires computational methods capable of identifying, retrieving, grounding, reasoning over, generating, and evaluating narrative representations. For nearly a decade, Text2Story has served as a leading venue for research on narrative extraction, understanding, representation, and generation from text. The 2027 edition expands this vision toward Narrative Intelligence: computational approaches for retrieving, interpreting, grounding, reasoning over, generating, and evaluating narratives across textual, multimodal, and interactive settings. This evolution reflects recent advances in Large Language Models (LLMs), retrieval-augmented generation (RAG), long-context architectures, and agentic AI, which increasingly enable narrative-aware computational systems while simultaneously introducing challenges related to grounding, temporal consistency, hallucinations, trustworthiness, bias, and explainability. The workshop will emphasize the growing convergence of Information Retrieval (IR), Natural Language Processing (NLP), multimodal AI, and narrative-centric reasoning, fostering interdisciplinary discussion on methods, resources, and evaluation frameworks for narrative-aware AI systems and their societal implications.
Research works submitted to the workshop should foster scientific advances in all aspects of narrative intelligence, including narrative extraction, retrieval, grounding, reasoning, generation, and evaluation across textual, multimodal, and interactive environments. Topics of interest include, but are not limited to, narrative understanding, retrieval-augmented generation, formal representation, knowledge extraction, multimodal narrative analysis, agentic AI, trustworthy narrative systems, and visualization of narratives.
The main goal of Text2Story’27 is to advance research on Narrative Intelligence: computational approaches for retrieving, understanding, representing, generating, grounding, and reasoning over narratives across textual, multimodal, and interactive environments. The workshop aims to bring together researchers and practitioners from Information Retrieval (IR), Natural Language Processing (NLP), Artificial Intelligence (AI), Machine Learning (ML), Computational Social Science, and Digital Humanities to discuss emerging challenges and methodologies for narrative-centric AI systems. In particular, it focuses on the growing convergence of IR, Large Language Models (LLMs), multimodal AI, and agentic systems as foundations for next-generation narrative understanding and generation.
The workshop seeks to advance the following research directions:
We expect contributions from researchers addressing all aspects of narrative extraction, representation, analysis, and generation. This includes the detection and formal modeling of events, participants, and their temporal and causal relations, as well as methods for reasoning and ordering. Submissions that explore narrative comprehension and interpretation, such as the analysis or evaluation of LLM-generated narratives, are particularly encouraged.
We also invite work on innovative ways to present and interact with narrative information, including automatic timeline construction, multimodal summarization, and narrative visualization. Research tackling misinformation, bias, and verification of extracted facts, along with the development of datasets, annotation schemas, and evaluation methodologies, is highly valued. Contributions addressing low and medium-resource languages, multilingual and cross-lingual settings are especially welcome.
Building on these themes, the field now faces pressing questions that can guide authors in shaping their submissions. How can LLMs and Agentic AI be leveraged for more coherent, grounded, and explainable narrative understanding? What strategies enable the integration of multimodal content—text, image, audio, video—into unified and trustworthy narratives? How can models dynamically adapt to evolving narratives across domains, genres, and languages? What methods best support the evaluation and benchmarking of narrative systems, from extraction to generation and reasoning? How can we ensure transparency, fairness, and robustness in narrative systems that may influence real-world perceptions and decisions? To what extent can collaboration between human experts and automated systems enhance interpretability, cultural awareness, and inclusivity in narrative understanding?
Original and high-quality unpublished contributions to the theory and practical aspects of the narrative extraction task. Full papers should introduce existing approaches, describe the methodology and the experiments conducted in detail. Negative result papers to highlight tested hypotheses that did not get the expected outcome are also welcomed.
Unpublished short papers describing work in progress; position papers introducing a new point of view, a research vision or a reasoned opinion on the workshop topics; and dissemination papers describing project ideas, ongoing research lines, case studies or summarized versions of previously published papers in high-quality conferences/journals that is worthwhile sharing with the Text2Story community, but where novelty is not a fundamental issue.
Unpublished papers presenting research/industrial demos; papers describing important resources (datasets or software packages) to the Text2Story community;
Papers must be submitted electronically in PDF format through Easy Chair . All submissions must be in English and formatted according to the one-column CEUR-ART style with no page numbers. Templates, available in either LaTeX or ODT (LibreOffice) format, can be found in the following zip folder. Do not use Word for the ODT template. CEUR requires the use of the Libertinus font family. Instructions on installing these fonts are found in the ODT template. There is also an Overleaf page for LaTeX users. Please also note that your work must include a Declaration on Generative AI to comply with the CEUR-WS GenAI policy. Both the LaTeX and LibreOffice templates already include this required section.
IMPORTANT: Please include between brackets the type of submission (full; negative results; work in progress; demo and resource; position; dissemination) in the paper title.
Papers submitted to Text2Story 2027 should be original work and different from papers that have been previously published, accepted for publication, or that are under review at other venues. Exceptions to this rule are "dissemination papers". Pre-prints submitted to ArXiv are eligible.
All papers will be refereed through a double-blind peer-review process by at least two members of the programme committee. We plan to publish the workshop proceedings as a CEUR volume, which will ensure they are indexed by DBLP and made available online via open access. Authors are therefore responsible for ensuring that their submissions do not infringe on any existing publication rights.
Text2Story 2027 will be held at the 49th European Conference on Information Retrieval (ECIR'27) in Southampton, United Kingdom.
Registration at ECIR 2027 is required to attend the workshop (don't forget to select the Text2Story workshop).
