29.998, Calls: Spanish, Catalan-Valencian-Balear, Applied Ling, Comp Ling, Text/Corpus Ling/Spain

[The LINGUIST List]

LINGUIST List: Vol-29-998. Mon Mar 05 2018. ISSN: 1069 - 4875.

Subject: 29.998, Calls: Spanish, Catalan-Valencian-Balear, Applied Ling, Comp Ling, Text/Corpus Ling/Spain

Moderators: linguist at linguistlist.org (Damir Cavar, Malgorzata E. Cavar)
Reviews: reviews at linguistlist.org (Helen Aristar-Dry, Robert Coté,
                                   Michael Czerniakowski)
Homepage: http://linguistlist.org

Please support the LL editors and operation with a donation at:
           http://funddrive.linguistlist.org/donate/

Editor for this issue: Kenneth Steimel <ken at linguistlist.org>
================================================================


Date: Mon, 05 Mar 2018 16:00:53
From: Mariona Taulé [mtaule at ub.edu]
Subject: IBEREVAL 2018 Task: MultiStanceCat: MultiModal Stance Detection in tweets on Catalan #1Oct Referendum

 
Full Title: IBEREVAL 2018 Task: MultiStanceCat: MultiModal Stance Detection in tweets on Catalan #1Oct Referendum 
Short Title: MultiStanceCat 

Date: 18-Sep-2018 - 18-Sep-2018
Location: Sevilla, Spain 
Contact Person: Mariona Taulé
Meeting Email: multistancetask2018 at gmail.com
Web Site: http://www.autoritas.net/MultiStanceCat-IberEval2018 

Linguistic Field(s): Applied Linguistics; Computational Linguistics; Text/Corpus Linguistics 

Subject Language(s): Catalan-Valencian-Balear (cat)
                     Spanish (spa)

Call Deadline: 29-Jun-2018 

Meeting Description:

The aim of the MultiStanceCat task is to detect the author's stance (in favor,
against or neutral) with respect to the Catalan #1Oct Referendum (2017) in
tweets written in Spanish and/or Catalan from a multimodal perspective. This
is a multimodal task because both the text of the tweet and the information
included in the link (when this information occurs) will be taken into account
when determining the stance. 

Stance detection is a task related to sentiment analysis, but unlike the
latter, in which the systems detect the positive, negative or neutral polarity
of the text, in stance detection the systems detect whether a text is
favorable or unfavorable to a topic of discussion, which is usually
controversial, and which may or may not be explicitly mentioned in the text.
The stance detection task is also related to a textual inference task due to
the fact that the position of the tweeter is often expressed implicitly,
therefore, the stance has to be inferred in many cases. Stance detection is
particularly interesting for studying political debates in which the topic is
controversial. Therefore, for this task we have chosen to focus on a specific
political issue: the Catalan #1Oct Referendum (2017).

In the training phase, participants will be provided with the TW-1OReferendum
training corpus manually annotated with stance. The possible stance labels
are: ‘favor’, ‘against’ and ‘neutral’. Later, the unlabeled test data will be
released. After the assessment, labels for the test data will also be
released.

There will be a session at IBEREVAL where the results of this shared task will
be discussed and the teams involved will present their results. 


Call for Participation:

IBEREVAL 2018:
Task: MultiStanceCat: MultiModal Stance Detection in tweets on Catalan #1Oct
Referendum

Webpage: http://www.autoritas.net/MultiStanceCat-IberEval2018

held in conjunction with the SEPLN 2018 International conference  at Hospital
Universitario Virgen del Rocío, Sevilla (Spain), on September 18, 2018.

The aim of the MultiStanceCat task is to detect the author's stance (in favor,
against or neutral) with respect to the Catalan #1Oct Referendum (2017) in
tweets written in Spanish and/or Catalan from a multimodal perspective. This
is a multimodal task because both the text of the tweet and the information
included in the link (when this information occurs) will be taken into account
when determining the stance.

Stance detection is a task related to sentiment analysis, but unlike the
latter, in which the systems detect the positive, negative or neutral polarity
of the text, in stance detection the systems detect whether a text is
favorable or unfavorable to a topic of discussion, which is usually
controversial, and which may or may not be explicitly mentioned in the text.
The stance detection task is also related to a textual inference task due to
the fact that the position of the tweeter is often expressed implicitly,
therefore, the stance has to be inferred in many cases. Stance detection is
particularly interesting for studying political debates in which the topic is
controversial. Therefore, for this task we have chosen to focus on a specific
political issue: the Catalan #1Oct Referendum (2017).

In the training phase, participants will be provided with the TW-1OReferendum
training corpus manually annotated with stance. The possible stance labels
are: ‘favor’, ‘against’ and ‘neutral’. Later, the unlabeled test data will be
released. After the assessment, labels for the test data will also be
released.

We cordially invite all researchers and practitioners from all fields to
participate in this task: MultiStanceCat: MultiModal Stance Detection in
tweets on Catalan #1Oct Referendum.

We also invite participants to subscribe to our Google group in order to be
kept up to date with the latest news related to the task:

MultiStanceCat-ibereval2018 at googlegroups.com

Important Dates

3 April 2018: Training corpus available
30 April 2018: Test corpus available
11 May 2018: Systems results
25 May 2018: Results notification
11 June 2018: Working papers submission
22 June 2018: Working papers revised (peer-reviewed)
29 June 2018: Final version of the revised Working papers (camera ready)
2 July 2018: Working papers and the Overview paper will be sent to the CEUR
Proceedings
18 September 2018: Workshop IberEval 2018 - MultiStanceCat task

Task Coordinators

Mariona Taulé, M. Antònia Martí (Universitat de Barcelona (UB), Spain)
Francisco Rangel (Autoritas Consulting, Spain)
Paolo Rosso (Universitat Politècnica de València (UPV), Spain)

Contact

E-mail: multistancetask2018 at gmail.com
Track Web page: MultiStanceCat-ibereval2018 at googlegroups.com




------------------------------------------------------------------------------

*****************    LINGUIST List Support    *****************
Please support the LL editors and operation with a donation at:
            http://funddrive.linguistlist.org/donate/
 


----------------------------------------------------------
LINGUIST List: Vol-29-998	
----------------------------------------------------------