Second Call for Papers

MultiLing 2019 Workshop in RANLP 2019

September 6th 2019

Varna, Bulgaria

Summarization and summary evaluation across source types and genres

MultiLing covers a variety of topics on Natural Language Processing, focused on the multilingual aspect of automatic summarization. As outlined in the overview page, the main scope of the workshop covers the following settings:

- Multilingual summarization across genres and sources
- Multilingual summary evaluation

In light of these directions, we invite submissions on the following (non-exhaustive) list of topics:

- Multilingual and cross-lingual summarization (main focus, horizontal across all other topics)
- Single-document summarization
- Multi-document summarization
- Summarization evaluation
- Headline generation
- Cross-domain/cross-topic summarization
- Summarization in different genres and sources (news, social media, fora, transcripts, literature, etc.)
- Sentiment/opinion summarization
- Multilingual/cross-lingual summarization corpus creation
- Machine learning for summarization
- Research works building upon previous and current MultiLing community tasks (elaborated below in the Community Tasks section)

In all the above topics we encourage authors to:
- support repeatability of experiments (through sharing data, tools, algorithm implementations);
- demonstrate the reusability and scope of methods by applying them on different datasets;
- provide insights related to strengths and weaknesses of methods;
- build upon existing MultiLing tasks and datasets, but not limit themselves to these.

Important dates:

The key dates of the workshop are listed below:

Papers submission deadline: 11 July 2019 21 July 2019
Papers acceptance notification: 28 July 2019

Submissions process:

Workshop paper submissions will be managed by the START submission system, selecting the 'Workshop Paper' submission type . Submissions should conform to the RANLP 2019 guidelines:

Submission  format:
Submitted manuscripts should follow strictly the ACL based stylesheets (provided here) and should not exceed 8 pages (+2 for references). The reviewing process will be blind: papers must not include the authors' names and affiliations, neither self-references that reveal the authors' identity. Please avoid "We previously proved (James, 2009) ...", and use instead citations such as "James previously proved (James 2009)...". Papers that do not conform with these requirements will be rejected without review.


Make sure you revisit:

frequently,  for updated information.

Community Tasks:
Along with the regular papers, Multiling 2019 offers community tasks for participation, not restricted by the aforementioned dates:

* Headline generation

The objective of this task is to explore some of the challenges highlighted by current state of the art approaches on creating informative headlines to news articles: non-descriptive headlines, out-of-domain training data, and generating headlines from long documents.

* Financial narrative summarization

This task aims to demonstrate the value and challenges of applying summarization to financial text, usually referred to as financial narrative disclosures.

* Summary evaluation

This task aims to examine how well automated systems can evaluate summaries from different languages.

For more information, see the call for participation on the community tasks.

About Multiling:
The first MultiLing was implemented as a pilot in TAC 2011, aiming to focus on the multilingual aspect of summarization. The momentum of the community gave birth to the biennial cycle of MultiLing workshops with MultiLing 2013 (in ACL 2013), MultiLing 2015 (in SIGDIAL 2015), MultiLing 2017 (in EACL 2017) and now Multiling 2019 in RANLP 2019. The number of interested and participating research groups in MultiLing has grown from 8 (in 2011) to more than 20 today, while the current community members in the MultiLing website are around 50.

Originally, MultiLing built upon community tasks in a multilingual setting: single- and multi-document summarization, summary evaluation, online fora summarization, transcript summarization. As in the 2017 workshop, this year we welcome submissions beyond the community tasks, aiming to further increase the scope and impact of the workshop. This welcomes submissions from contributors beyond the task participants, regarding experiments on existing results, as well as extensions of previous works with significant added value (e.g. new experiments, new findings, deepend study).

For more information, visit the MultiLing community website and the MultiLing 2019 overview page.

George Giannakopoulos - NCSR Demokritos (General Chair, Summary Evaluation Task)
John M. Conroy - IDA Center for Computing Sciences (Headline Generation Task)
Marina Litvak - Sami Shamoon College of Engineering (Headline Generation Task)
Peter Rankel - Elder Research Inc. (Headline Generation Task)
Mahmoud El-Haj - University of Lancaster (Financial Narrative Summarization Task)

Invited Speakers:
Horacio Saggion - Universitat Pompeu Fabra

Programme Committee:
John M. Conroy - IDA Center for Computing Sciences
Marina Litvak - Sami Shamoon College of Engineering
Udo Kruschwitz - University of Essex
Horacio Saggion - Universitat Pompeu Fabra
Elena Lloret - University of Alicante
Vangelis Karkaletsis - NCSR Demokritos
Mark Last - Ben-Gurion University of the Negev
Natalia Vanetik - Sami Shamoon College of Engineering, Ben-Gurion University of the Negev
Josef Steinberger - University of West Bohemia
Laura Plaza - UNED
Florian Boudin - University of Nantes
Iraklis Varlamis - Harokopio University
George Petasis - NCSR Demokritos
Peter Rankel - Elder Research Inc.
George Giannakopoulos - NCSR Demokritos
Mahmoud El-Haj - Lancaster University
Ahmet Aker - Universität Duisburg-Essen
Giuseppe Riccardi - University of Trento
Corina Forascu - University "Al. I. Cuza" Iasi
Michalis Vazirgiannis - Ecole Polytechnique; Athens University of Economics and Business