April 14th, 2019 - Cologne, Germany

Text2Story 2019

Second International Workshop on Narrative Extraction from Texts
held in conjunction with the 41st European Conference on Information Retrieval

Call for papers

Call for papers

The increasing availability of text information in the form of news articles, comments or posts poses new challenges for those who aim to understand the storyline of an event. Although understanding natural language text has improved over the last couple of years with several research works emerging on the grounds of information extraction and text mining, the problem of constructing consistent narrative structures is yet to be solved. We still have a challenging path ahead of us for the development and improvement of algorithms that automatically identify, interpret and relate the different elements of a narrative which will be likely spread from different sources.

Research works submitted to the workshop should foster the scientific advance on all aspects of storyline generation from texts including but not limited to narrative and content generation, formal representation, and visualization of narratives. This includes the following topics (not limited):

  • Event Identification
  • Narrative Representation Language
  • Sentiment and Opinion Detection
  • Argumentation Mining
  • Narrative Summarization
  • Multi-modal Summarization
  • Storyline Visualization
  • Temporal Aspects of Storylines
  • Story Evolution and Shift Detection
  • Causal Relation Extraction and Arrangement
  • Evaluation Methodologies for Narrative Extraction
  • Big data applied to Narrative Extraction
  • Resources and Dataset showcase
  • Personalization and Recommendation
  • User Profiling and User Behavior Modeling
  • Models for detection and removal of bias in generated stories
  • Ethical and fair narrative generation
  • Bias in Text Documents
  • Automatic Timeline Generation
  • Credibility
  • Fact Checking
  • Bots Influence

Important Dates

  • Submission deadline: February 11th, 2019
  • Acceptance Notification Date: March 11th, 2019
  • Camera-ready copies: March 22nd, 2019
  • Workshop: April 14th, 2019

Submissions

We invite two kinds of submissions:

  • Research papers (max 7 pages + references)
  • Demos and position papers (max 5 pages + references)

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

Submissions will be peer-reviewed by at least three members of the programme committee. The accepted papers will appear in the proceedings published at CEUR workshop proceedings (usually indexed on DBLP). Participants of accepted papers will be given 15 minutes for oral presentations. All papers will also be also presented in an interactive poster session.

Organization

Organization Committee

Program Committee

  • Álvaro Figueira (University of Porto)
  • Arian Pasquali (University of Porto)
  • Bruno Martins (IST and INESC-ID - Instituto Superior Técnico, University of Lisbon)
  • Conceição Rocha (INESC TEC)
  • Daniel Loureiro (University of Porto)
  • Daniel Gomes (FCT/Arquivo.pt)
  • Dhruv Gupta (Max Planck Institute for Informatics)
  • Federico Nanni (University of Mannheim)
  • Florian Boudin (Université de Nantes)
  • Gaël Dias (Normandie University)
  • Gerasimos Lampouras (The University of Sheffield)
  • Henrique Lopes Cardoso (University of Porto)
  • Jacobo Rouces (University of Gothenburg)
  • João Magalhães (New University of Lisbon)
  • João Paulo Cordeiro (Universidade da Beira Interior)
  • Pablo Gamallo (University of Santiago de Compostela)
  • Paulo Quaresma (Universidade de Evora)
  • Mark Finlayson (Florida International University)
  • Marc Spaniol (Université de Caen Normandie)
  • Mengdie Zhuang (The University of Sheffield)
  • Miguel Martinez-Alvarez (Signal)
  • Nicola Ferro (University of Padova)
  • Nina Tahmasebi (University of Gothenburg)
  • Nuno Moniz (LIAAD/INESC TEC)
  • Udo Kruschwitz (University of Essex)
  • Sérgio Nunes (University of Porto)
  • Yihong Zhang (Kyoto University)
  • Vitor Mangaravite (LIAAD INESC TEC)

Proceedings Chair

  • Conceição Rocha (INESC TEC)
  • João Paulo Cordeiro (Universidade da Beira Interior)

Web and Dissemination Chair

  • Arian Pasquali (University of Porto)
  • Vitor Mangaravite (LIAAD INESC TEC)

Invited Speakers

Claim Validation by Humans and Machines: Where We Are and the Road Ahead

Speaker: Prof. Iryna Gurevych, Technische Universität Darmstadt

Abstract: Claim validation is a highly demanding expert task which prevents the proliferation of mis-information. In the recent years, we have seen a rapidly increasing interest in this problem domain. This interest is due to both the task significance and the impressive advances in AI-/NLP-based approaches. The talk will present novel datasets and problem definitions and experimental results related to automated claim validation. Besides, it will discuss our recent work on open-domain argument retrieval and clustering for human claim validation. We will conclude by outlining some open challenges for future research.

Bio: Iryna Gurevych is a Professor in the Department of Computer Science at the Technische Universität Darmstadt, Germany. She is the founding Director of the UKP Lab an of the Research Training Group "Adaptive Preparation of Information from Heterogeneous Sources" (AIPHES), funded by the German Research Foundation. Iryna has a broad range of research interests in natural language processing, with a focus on computational argumentation, computational lexical semantics, question answering and summarization. She has recently served as the PC Co-Chair of ACL 2018 in Melbourne, Australia. Also, she co-founded and co-organized the workshop series "Collaboratively Constructed Semantic Resources and their Applications to NLP" and "Argument Mining". She co-authored the book "Linked Lexical Knowledge Bases: Foundations and Applications" (2016). She is the recipient of the Emmy Noether Early Career Award from the German Research Foundation (2007) and the interdisciplinary Lichtenberg Professorship Award by the Volkswagen Foundation (2008). Further information click here.

Automatic Media analysis: From monitoring to Insights

Speaker: Miguel Martinez, Chief Data Scientist at Signal Media

Abstract: One of the aspects of media analysis is brand monitoring which has traditionally focused on detecting and distributing every mention of a given brand in the media as quickly as possible. This monitoring aspect, which some companies such as Signal have automated using different IR and ML techniques, is critical for finding relevant information. However, retrieving these documents is not enough. Leaders in diverse organisations will use the knowledge derived from these relevant documents to change their decision making by understanding their risks, opportunities (e.g. Acquiring companies in distress or expanding to new territories), but this is not possible manually. Techniques to understand, organise and uncover the underlying insights that are hidden in the thousands of documents are needed.

This talk will focus on the media analysis space, the current monitoring approach (using Signal as an example) and the future challenges and opportunities in the insights space, showcasing different challenges in the space and that the IR community could support with.

Bio: Miguel Martinez is the co-founder and Chief Data Scientist of Signal, a growing UK company that analyses millions of news articles every day in real-time in order to improve business intelligence and decision making. During the last 6 years, Miguel has led the efforts to create and maintain the Signal Research team with strong university collaborations, with the main goal of transforming the best research principles, models and algorithms from academia into real, scalable products. Research interests include news processing, information retrieval, text analysis, natural language processing and evaluation, among others. He completed his PhD from Queen Mary University in 2014. During his time at Signal, the company has grown from 3 to more than 100 people in 3 continents and raised more than $30M. He has been awarded the Business Leader of Tomorrow award 2014 by Innovate UK and was included in the list of UK Business Innovators in 2016 by Bloomberg. Signal has won numerous awards, including the Fujitsu AI Innovator in the Lloyds National Business awards 2018 and the Hottest Enterprise SaaS or B2B in the Europas 2018. The team has also won the Best Demonstration award in ECIR’15 and they are the main organisers of the NewsIR workshop.

Programme

Download slides and photos .
09:00 – 09:10: Introduction
09:10 – 09:50: Keynote 1: Automatic Media analysis: From monitoring to Insights
(Miguel Martinez-Alvarez)
09:50 – 10:10: Automatic Recognition of Narrative Drama units: a structured learning approach
(Roberto Basili, Danilo Croce , Vincenzo Lombardo, Eleonora Ceccaldi)
10:10 – 10:30: Semantic Storytelling: Towards Identifying Storylines in Large Amounts of Text Content
(Karolina Zaczynska, Georg Rehm, Julián Moreno)
10:30 – 11:00: Coffee break
11:00 – 11:20: NOVEL2GRAPH: Visual Summaries of Narrative Text Enhanced by Machine Learning
(Alessandro Antonucci, Vani K)
11:20 – 11:40: Towards the Automatic Analysis of the Structure of News Stories
(Riza Batista-Navarro, Iqra Zahid,Hao Zhang, Frank Boons)
11:40 – 12:00: Automated Event Extraction Model for Linked Portuguese Documents
(Kashyap Raiyani, Paulo Quaresma, Teresa Gonçalves, Vitor Nogueira)
12:00 – 12:30: Poster Session
12:30 – 13:30: Lunch break
13:30 – 14:10: Keynote 2: Claim Validation by Humans and Machines: Where We Are and the Road Ahead
(Iryna Gurevych)
14:10 – 14:30: Steps Towards a System to Extract Formal Narratives from Text
(Daniele Metilli,Valentina Bartalesi, Carlo Meghini)
14:30 – 14:50: Textual Analysis for Radicalisation Narratives aligned with Social Sciences Perspectives
(Ronald Denaux, Jose Manuel Gomez-Perez)
15:00 – 15:30: Coffee break
15:30 – 15:50: Dense vs. Sparse Representations for News Stream Clustering
(Todor Staykovski, Alberto Barrón-Cedeño, Giovanni Da San Martino, Preslav Nakov)
15:40 – 16:10: Narrative detection in online patient communities
(Anne Dirkson,Suzan Verberne, Wessel Kraaij)
16:10 – 16:30: Extracting Evidence Summaries from Detective Novels
(Aditya Motwani, Aayush Naik, Kamalakar Karlapalem)
16:30 – 17:00: Demo showcase

Public demos

TopExNet
Topic Exploration in Entity-centric Networks of News Streams by Andreas Spitz and Satya Almasian from Heidelberg University
http://topexnet.ifi.uni-heidelberg.de

TanBih
News bias and media outlets profiles by Preslav Nakov and Qatar Computing Research Institute
http://www.tanbih.org

ArgumentSearch
Argumentation mining search engine by Iryna Gurevych and Technische Universität Darmstadt
http://argumentsearch.com

Agatha
Platform for Criminal Police Investigation by Kashyap Raiyani
http://www.agatha-osi.com/

YAKE Keyword Extraction
Unsupervised single-document keyword extraction by Arian Pasquali, Vitor Mangaraviti, Ricardo Campos and LIAAD
http://yake.inesctec.pt

Tell me stories
Temporal summarization by Arian Pasquali, Vitor Mangaraviti, Ricardo Campos and LIAAD
Portuguese Web Archive http://archive.tellmestories.pt, ECIR demo http://demo.tellmestories.pt

The Venue

The conference will be held in Cologne, Germany.
Maternushaus
Tagungszentrum des Erzbistums Köln
Kardinal-Frings-Str. 1-3
50668 Köln

More information http://www.ecir2019.org/venue/