January 7th and 8th, 2021 - Virtual Yokohama, Japan


Artificial Intelligence for Narratives Workshop held in conjunction with the 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence

Call for papers

Call for papers

Narratives are an important human tool for communication, representation and understanding. Natural Language Processing already offers many instruments that enable the automatic extraction of narrative elements from texts, including Named Entity Recognition, Semantic Role Labeling, Sentiment Analysis, Anaphora Resolution, Temporal Reasoning, etc. The storyfication of data is being used to generate textual reports on finance and sports, among others. Timelines and infographics can be employed to represent in a more compact way automatically identified narrative chains in a large set of news articles, assisting human readers in grasping complex stories with different moments and a network of characters. While the Automatic Generation of Text shows impressive results towards computational creativity, it still needs to develop means for controlling the narrative intent of the output. Automatically Generated Narratives can also be used to summarize videos in different applications (health care, surveillance and safety, sports, etc.) or sensor data. They can also be useful for Explainable AI, Algorithmic Transparency, developing Trust on AI users and generally enabling rich Human-AI interaction.

It is therefore important to gather the knowledge on AI means, concepts and tools for Narrative Extraction, Representation and Generation and to join the AI community on these topics. This includes AI fields such as NLP, Machine Learning, Knowledge Representation, Inference, Planning, Graphical Communication and Image Processing. Applications include health care (patient stories), media (news outlets), communication science, business and reporting (data stories), industry (transparency) and arts (story generation, graphical depiction of stories).

This workshop aims to bring together AI researchers and practitioners working on the topic of Narratives, mainly for those working on NLP, but open to other relevant inputs in this emerging area. We invite researchers and practitioners to submit research papers, application papers, project summary papers and demo papers. Each paper will be presented either orally or as a demo.

Contributions on the following topics are welcome, as well as on other non listed but highly relevant topics:

  • Narrative Extraction from text, including social media
  • Narrative Understanding
  • Storyfication of non-textual data, including image, video, financial, weather, sports and sensor data
  • Narrative formalisation and reasoning on narratives, including representation formalisms and narrative calculus
  • Representing Narratives graphically or in other forms of communication, including infographics, cartoons, slide shows, video-clips, video-games, etc
  • Generation of textual narratives, including narrative construction, narrative creation, planning and problem solving for narratives
  • Narrative Temporal Reasoning
  • Bias in Narrative Generation
  • Applications of narrative extraction and generation, including media, health care, science, sports, industry, business and administration, education, recommender systems and XAI
  • Evaluation methodologies for Narrative Extraction and Generation
  • Related methods for narrative construction including abstractive summarization, reinforcement learning, transfer learning and so on

Accepted works will be assigned oral presentations and/or demo slots and/or poster presentations.

All papers will be made available as CEUR Workshop Proceedings. We intend to launch a journal special issue on the topic.

Important Dates

  • Submission deadline: April 23rd, 2020 April 30rd, 2020 May 10th, 2020 (extended)
  • Acceptance Notification Date: June 22nd, 2020
  • Camera-ready copies: June 30th, 2020
  • Workshop: January 7 and 8, 2021


We encourage the following kinds of submissions:

  • Research papers (max 6 pages + references) with original work, promoting and sharing exciting new ideas and fostering discussion or describing well founded impactful applications
  • Demo papers (max 3 pages + references) describing relevant tools
  • Position papers (max 3 pages + references) describing relevant and supported points of view, including description of ongoing projects
  • Nectar papers (max 3 pages + references) with a summary of work published in other conferences or journals that is worthwhile sharing with the community

All papers must be formatted according to the IJCAI format style. Papers must be submitted electronically in PDF format through our Easy Chair link.

Submissions will be peer-reviewed by at least two members of the programme committee. The accepted papers will appear in the proceedings published at CEUR workshop proceedings (usually indexed on DBLP). We also plan to launch a journal special issue on the topic.


Organizing Committee

Proceedings Chair

  • João Paulo Cordeiro (INESC TEC; Universidade da Beira do Interior, Covilhã, Portugal)

Media and Dissemination Chair

  • Arian Pasquali (INESC TEC)
  • Brenda Santana (UFRGS & INESC TEC)
  • Behrooz Mansouri (Rochester Institute of Technology, Rochester, NY, USA)
  • Shamsuddeen Muhammad (INESC TEC)

Review Support Chair

  • Daniel Loureiro (INESC TEC, Portugal)

Program Committee

  • Álvaro Figueira (University of Porto)
  • Andreas Spitz (École polytechnique fédérale de Lausanne)
  • António Branco (Universidade de Lisboa)
  • Arian Pasquali (INESC TEC)
  • Bruno Martins (IST and INESC-ID - Instituto Superior Técnico, University of Lisbon)
  • Daniel Loureiro (University of Porto)
  • Dennis Aumiller (Heidelberg University)
  • Dhruv Gupta (Max Planck Institute for Informatics)
  • Dwaipayan Roy (GESIS - Leibniz Institute for the Social Sciences)
  • Florian Boudin (Université de Nantes)
  • Georgiana Ifrim (University College Dublin)
  • Grigorios Tsoumakas (Aristotle University of Thessaloniki)
  • Joeran Beel (Trinity College Dublin)
  • Jeremy Pickens (OpenText)
  • John Shaw-Taylor (University College London)
  • Kiran Kumar Bandeli (Walmart Inc.)
  • Marc Spaniol (Université de Caen Normandie)
  • Mark Finlayson (Florida International University)
  • Muhammad Syafiq Mohd Pozi (Universiti Utara Malaysia)
  • Naoya Inoue (Tohoku University)
  • Nuno Moniz (INESC TEC)
  • O-Joun Lee (Pohang University of Science and Technology)
  • Ondrej Dusek (Charles University)
  • Pablo Gervás (Universidad Complutense de Madrid)
  • Panote Siriaraya (Kyoto Institute of Technology)
  • Paulo Quaresma (Universidade de Évora)
  • Satya Almasian (Heidelberg University)
  • Sebastião Miranda (Priberam)
  • Sérgio Nunes (University of Porto)
  • Takashi Ogata (Iwate Prefectural University)
  • Vítor Mangaravite (Universidade Federal de Minas Gerais)
  • Vincenzo Lombardo (Università di Torino)
  • Yijun Duan (Kyoto University)
  • Yihong Zhang (Osaka University)
  • Zhiwen Tang (Georgetown University)

Invited Speakers

Ants Have Megaphones Now: Text Mining and Summarization for News and Social Media Streams

  • Speaker: Georgiana Ifrim (Insight SFI Centre for Data Analytics | VistaMilk SFI Research Centre | University College Dublin, Ireland)

Comixify: turning videos into comics

  • Speaker: Tomasz Trzcinski (Comixify.com)
  • Abstract: In this talk, we would like to tell you about Comixify® - AI-powered tool that turns videos into comics. It is a result of a research project run at Warsaw University of Technology with a group of students, that since it’s release in December 2018 became a massive success with over 200'000 visitors to our website and over 30'000 generated comics. The algorithm behind Comixify consists of two parts: first we select representative and visually pleasant frames from a video using a combination of reinforcement learning and a convolutional neural network approach, based on our previous research on popularity estimation in social media. Afterwards, we convert the style of the frames using our own ComixGAN architecture based on generative adversarial networks. In this talk, using Comixify as a case study, we will give an introduction to how machine learning can improve understanding narratives and what future research paths we envision to incorporate more multimodal cues into our engine.


  • 7th January (times indicated in UTC)
  • 09:00 - 10:00      Keynote 1. Ants Have Megaphones Now: Text Mining and Summarization for News and Social Media Streams - Georgiana Iffrim
  • 10:00 - 10:30      IdeaNet: Potential Opportunity Discovery for Business Innovation - O-Joun Lee, Sung Youn Park and Jin-Taek Kim
  • 10:00 - 10:30      Coffe Break
  • 11:00 - 11:30      THEaiTRE: Artificial Intelligence to Write a Theatre Play - Rudolf Rosa, Ondřej Dušek, Tom Kocmi, David Mareček, Tomáš Musil, Patrícia      Schmidtová, Dominik Jurko, Ondřej Bojar, Daniel Hrbek, David Košťák, Martina Kinská, Josef Doležal and Klára Vosecká
  • 11:30 - 12:00      Finite State Machines and Live Emergent Narrative Theatre. - Craig Green
  • 12:00 - 12:30      Storytelling AI: A Generative Approach to Story Narration - Sonali Fotedar, Koen Vannisselroij, Shama Khalil and Bas Ploeg
  • 12:30 - 13:00      Relation Clustering in Narrative Knowledge Graphs - Simone Mellace, Vani K and Alessandro Antonucci
  • 8th January (times indicated in UTC)
  • 08:00 - 09:00      Keynote 2. Comixify: turning videos into comics - Tomasz Trzcinski
  • 09:00 - 09:30      Mastering the Media Hype: Methods for Deduplication of Conflict Events from News Reports - Vanni Zavarella, Camelia Ignat, Jakub Piskorski, Hristo Tanev and Martin Atkinson
  • 09:30 - 10:00      A Rule-Based Model of Emotion Appraisal for Narratives - Vincenzo Lombardo
  • Coffe Break
  • 10:30 - 11:00      Confirming the Generalizability of a Chain-Based Animacy Detector - Labiba Jahan, W. Victor H. Yarlott, Rahul Mittal and Mark A. Finlayson
  • 11:00 - 11:30      Story Fragment Stitching: The Case of the Story of Moses - Mohammed Aldawsari, Ehsaneddin Asgari and Mark Finlayson
  • 11:30 - 13:00      Socializing

The Venue

Virtual Yokohama, Japan

More information can be found ont the IJCAI web site