[Air-L] Final Call for Papers and Shared Task Participation (CASE @ EMNLP 2022): Challenges and Applications of Automated Extraction of Socio-political Events from Text

[ali hürriyetoglu]

Apologies for cross-posting!

************************************************************************************

URL: https://emw.ku.edu.tr/case-2022/

Sep 7, 2022: Submission deadline on Softconf

Jul 15, 2022: Latest ARR submission deadline for ARR

Oct 2, 2022: Latest ARR commitment deadline

Oct 9, 2022: Notification of Acceptance

Oct 16, 2022: Camera-ready papers due

Workshop dates: Dec 7-8, 2021

Location: Hybrid -> Abu Dhabi & Online

Please see below for the important dates of the shared tasks.

There are two options for submissions that are i) Softconf page of the
workshop: https:// <https://www.softconf.com/m/icspcc2022>
softconf.com/emnlp2022/case2022 and ii) ACL Rolling review (ARR):
https://aclrollingreview.org/dates.

************************************************************************************

Event extraction has long been a challenge for the natural language
processing (NLP) community as it requires sophisticated methods in defining
event ontologies, creating language resources, domain specific grammars,
developing Machine Learning models and other algorithmic approaches for
various event-detection- specific tasks, such entity detection, semantic
labeling, event classification and clustering and others (Pustojevsky et
al. 2003; Boroş, 2018; Chen et al. 2021). Social and political scientists
have been working to create socio-political event (SPE) databases such as
ACLED, EMBERS, GDELT, ICEWS, MMAD, PHOENIX, POLDEM, SPEED, TERRIER, and
UCDP following similar steps for decades. These projects and the new ones
increasingly rely on machine learning (ML), deep learning (DL), and NLP
methods to deal better with the vast amount and variety of data in this
domain (Hürriyetoğlu et al. 2020). Unfortunately, automated approaches
suffer from major issues like bias, limited generalizability, class
imbalance, training data limitations, and ethical issues that have the
potential to affect the results and their use drastically (Lau and Baldwin
2020; Bhatia et al. 2020; Chang et al. 2019). Moreover, the results of the
automated systems for SPE information collection have neither been
comparable to each other nor been of sufficient quality (Wang et al. 2016;
Schrodt 2020). SPEs are varied and nuanced. Both the political context and
the local language used may affect whether and how they are reported.

We invite contributions from researchers in computer science, NLP, ML, DL,
AI, socio-political sciences, conflict analysis and forecasting, peace
studies, as well as computational social science scholars involved in the
collection and utilization of SPE data. This includes (but is not limited
to) the following topics

1) Extracting events in and beyond a sentence, event coreference
resolution,

2) New datasets, training data collection, and annotation for event
information,

3) Event-event relations, e.g., subevents, main events, causal relations,

4) Event dataset evaluation in light of reliability and validity metrics,

5) Defining, populating, and facilitating event schemas and ontologies,

6) Automated tools and pipelines for event collection related tasks,

7) Lexical, syntactic, discursive, and pragmatic aspects of event
manifestation,

8) Methodologies for development, evaluation, and analysis of event
datasets,

9) Applications of event databases, e.g. early warning, conflict
prediction, policymaking,

10) Estimating what is missing in event datasets using internal and
external information,

11) Detection of new SPE types, e.g. creative protests, cyberactivism,
COVID19 related,

12) Release of new event datasets,

13) Bias and fairness of the sources and event datasets,

14) Ethics, misinformation, privacy, and fairness concerns pertaining to
event datasets, and

15) Copyright issues on event dataset creation, dissemination, and sharing.

16) We encourage submissions of new system description papers on our
available benchmarks (ProtestNews @ CLEF 2019, AESPEN @ LREC 2020, and CASE
@ 2021). Please contact the organizers if you would like to access the
data.

The proceedings of the previous editions should be indicative of what we
cover: ProtestNews @ CLEF 2019 (http://ceur-ws.org/Vol-2380/), AESPEN @ ACL
2020 (https://aclanthology.org/volumes/2020.aespen-1/), CASE @ ACL-IJCNLP
2021 (https://aclanthology.org/volumes/2021.case-1/).


**** Shared tasks ****

Task 1- Multilingual protest news detection: This is the same shared task
organized at CASE 2021 (For more info:
https://aclanthology.org/2021.case-1.11/) But this time there will be
additional data and languages at the evaluation stage. Contact person: Ali
Hürriyetoğlu (ali.hurriyetoglu at gmail.com). Github:
https://github.com/emerging-welfare/case-2022-multilingual-event

Task 2- Automatically replicating manually created event datasets: The
participants of Task 1 will be invited to run the systems they will develop
to tackle Task 1 on a news archive (For more info
https://aclanthology.org/2021.case-1.27/). Contact person: Hristo Tanev (
htanev at gmail.com). Github:
https://github.com/emerging-welfare/case-2022-multilingual-event

Task 3- Event causality identification: Causality is a core cognitive
concept and appears in many natural language processing (NLP) works that
aim to tackle inference and understanding. We are interested to study event
causality in news, and therefore, introduce the Causal News Corpus. The
Causal News Corpus consists of 3,559 event sentences, extracted from
protest event news, that have been annotated with sequence labels on
whether it contains causal relations or not. Subsequently, causal sentences
are also annotated with Cause, Effect, and Signal spans. Our two subtasks
(Sequence Classification and Span Detection) work on the Causal News
Corpus, and we hope that accurate, automated solutions may be proposed for
the detection and extraction of causal events in news. Contact person:
Fiona Anting Tan (tan.f at u.nus.edu). Github:
https://github.com/tanfiona/CausalNewsCorpus



**** Deadlines for the Shared tasks ****

** Task 1 & 2:

Training data available: The training data from CASE 2021 is used.

New test data available: Sept 15, 2022

Test end: Sep 25, 2022

System Description Paper submissions due: Oct 2, 2022

Notification to authors after review: Oct 09, 2022

Camera-ready: Oct 16, 2022

** Task 3:

Training and validation data available: Apr 15, 2022

Validation labels and test data available: Aug 01, 2022

Test phase: Aug 01, 2022 - Aug 31, 2022 (extended from Aug 15)

System Description Paper submissions due: Sep 07, 2022

Notification to authors after review: Oct 09, 2022

Camera ready: Oct 16, 2022

*** Keynotes ***

i) J. Craig Jenkins (https://sociology.osu.edu/people/jenkins.12)

ii) Scott Althaus (https://pol.illinois.edu/directory/profile/salthaus)

iii) Thien Huu Nguyen (https://ix.cs.uoregon.edu/~thien/)

Submissions: Please see the workshop web page for additional details.