This e-mail only highlights the important bits of information. Visit for more.


Santa Fe, New Mexico, August, 2018

Workshop web site:



Submission deadline: May 25, 2018 11:59 PM PST

Notification of acceptance: June 20, 2018

Camera-ready copy due from authors:  June 30, 2018



Heng Ji, Edward P. Hamilton Development Chair Professor, Computer Science
Department of Rensselaer Polytechnic Institute



Following the success of last year’s edition of the 2017 EventStory workshop
<> at ACL, we
invite work on all aspects of event and storyline analysis, storyline
generation, and relationships between events and storylines or their
components, especially from news. This includes (but is not limited to) the
following topics:

- event detection (mentions and instances)

- identifying and filtering relevant events

- cumulation of information from news streams

- detecting opinions and perspectives on events

- tracing perspective change through time

- modeling plot structures

- storyline stability and completeness

- annotating storylines

- temporal or causal ordering of events

- event coreference (in-document and cross-document)

- sub-event and event subset relations

- temporal event sequencing

- script activation

- big data for storylines

- evaluation of storylines

- discourse structure and storylines

- visualisation of storylines

- dynamic event modeling

- counterfactuals modeling

- event factuality profiling

- multimodal storyline generation

- event representation



Two types of submissions are invited: full papers and short papers.

Full papers should emphasize obtained results rather than intended work,
and should indicate clearly the state of completion of the reported
results. Submission should not exceed a maximum 8 pages plus two additional
pages containing references.

Short papers may consist of up to 4 pages (plus two additional pages for
references) describing: a focused contribution; work in progress; a
negative result; a position paper.

The reviewing process will be blind and papers must be anonymous.

Submissions must be in PDF following the COLING 2018 style template. Style
files are available here

Multiple Submission Policy Papers that have been or will be submitted to
other meetings or publications are acceptable, but authors must indicate
this information at submission time. If accepted, authors must notify the
organizers as to whether the paper will be presented at the workshop or



To make the results of the workshop more effective, we are planning a “
working” workshop with an annotation exercise session. This year, the
organisers will provide a set of news articles and documents from different
sources concerning the MH17 disaster and the vaccination debate, reflecting
different perspectives and versions of the stories. The data set is
provided as a so-called unshared task for which participants can provide
their own annotations, interpretations, and analyses. We will collect these
analyses before the workshop and summarise them to facilitate an insightful
comparison. We will ask for clear documentation to enable meaningful
comparisons. Furthermore, we will ask participants who have systems and
tools for extracting events and/or storylines to run their systems on these
common datasets. The results will be compared as far as possible and

The Events and Stories in the News workshop will include an un-shared
annotation task on events and narrative structures in a small set of text
news articles.

Given a collection of raw texts concerning a specific story (thus, multiple
documents spreading in time), the aim of this unshared task is to tackle
fundamental research question in storylines identification and extraction.
Briefly, the participant(s) should propose a task with a corresponding
annotation scheme, conduct an annotation experiment, and evaluate strengths
and weakness of the task.

Papers should be submitted as standard workshop short papers (max 4 pages
length). They will be reviewed by the program committee and non-anonymous
reviews will be made available at the workshop website. Papers must mention
“unshared task” in their titles. The unshared task work will be presented
in a special poster session followed by an open discussion. Submissions of
the annotated data and accompanying annotation guidelines is strongly

More details are available at



   Tommaso Caselli, Rijksuniversiteit Groningen, NL

   Claire Bonial, U.S. Army Research Laboratory, USA

   Susan Brown, University of Colorado, USA

   David Caswell, Reynolds Journalism Institute, University of Missouri, USA

   Eduard Hovy, Language Technologies Institute, Carnegie Mellon
   University, USA

   Ben Miller, Georgia State University, USA

   Teruko Mitamura, Language Technologies Institute, Carnegie Mellon
   University, USA

   Martha Palmer, University of Colorado, USA

   Marieke van Erp, KNAW Humanities Cluster, NL

   Piek Vossen, Vrije Universiteit Amsterdam, NL

Tommaso Caselli, Ph.D.
Assistant Professor in Computational Semantics
Faculty of Arts, Rijksuniversiteit Groningen
The Netherlands
Twitter: @tommaso_caselli
UNSUBSCRIBE from this page:
Corpora mailing list

Reply via email to