LINGUIST List 28.749

Tue Feb 07 2017

Calls: Cog Sci, Comp Ling, Disc Analysis, Semantics, Text/Corpus Ling/Canada

Editor for this issue: Kenneth Steimel <>

Date: 06-Feb-2017
From: Tommaso Caselli <>
Subject: Events and Stories in the News
E-mail this message to a friend

Full Title: Events and Stories in the News

Date: 03-Aug-2017 - 04-Aug-2017
Location: Vancouver, Canada
Contact Person: Tommaso Caselli
Meeting Email: < click here to access email >
Web Site:

Linguistic Field(s): Cognitive Science; Computational Linguistics; Discourse Analysis; Semantics; Text/Corpus Linguistics

Call Deadline: 30-Apr-2017

Meeting Description:

Following the success of the two workshops on Computing News Storylines (CNewsStory, ACL 2015, CNewsStory, EMNLP 2016), the previous four editions of the EVENTS workshops (NAACL 2013, 2014, 2015, 2016), and the strong connections between these two initiatives, the organisers of the two series have decided to join efforts and propose this new workshop: Events and Stories in the News.

Traditionally, event structures have always been at the heart of linguistics. Nevertheless, NLP solutions seem to struggle with notions such as event detection, event identity and coreference, and causal, topical, temporal, and spatial relations between events.

Humans, on the other hand, easily notice salient events, such as changes in the world, make reference to these events and their participants through linguistic expressions, and construct storylines using only the pertinent aspects. Such narrative structures are at the heart of information sharing, as is exemplified by the structure of news articles. But it remains extraordinarily difficult to detect them automatically, let alone decide on pertinence for automated story construction from rich event representations.

Today's massive news streams demand multidimensional, multimodal, distributed representations of events and narrative structures that take the connections between all relevant elements involved in a ''story''. Currently, most work on cross-document temporal processing focuses on linear timelines, assuming a simple chronological ordering of events in time. However, not every timeline necessarily forms a good and useful storyline.

The Computing News Storylines workshops have focused on the analysis of news articles with regard to temporal and causal ordering. The EVENTS workshops provided a substantial contribution to the debate on the definition, representation, and detection of events, event coreference, event structure, slot filling, and multi-event sequences (scripts) in the NLP community. Connecting these two series (research in events and storylines) is of great importance for both fields of work; it can bring complementary solutions to pending issues concerning the representation and evaluation of storylines, events occurring in complex mentions, event coreference, event structure, event relations and scripts from which different research communities can benefit.

Call for Papers:

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
- Identifying and filtering relevant events
- Cumulation of information from news streams
- Detecting opinions and perspectives on events
- Tracing perspective change through time
- Modelling 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 modelling
- Counterfactuals modelling
- Event factuality profiling
- Multimodal storyline generation
- Event representation

Important Dates:

Submission deadline: April 30, 2017 11:59 PM PST
Notification of acceptance: May 19, 2017
Camera-ready copy due from authors: May 26, 2017

Submission Instructions:

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 ACL 2017 style template. Style files are available on the conference website,

Contributions should be submitted in PDF via the submission site:

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 elsewhere.

Shared Annotation Task:

We are providing documents from different sources, stretching over a period of time and focused on a specific topic and will ask the participants to provide their own annotations, interpretations, and analyses of this dataset. 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 this common dataset. These results will be compared to the annotated data (only indirect comparisons would be possible). Check the available corpora:

Page Updated: 07-Feb-2017